© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 95963
    Prev
    Next
    INDEX
    Explanations

    advantages and disadvantages

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that signal a pros/cons or implications-style discussion — i.e., discourse markers that introduce advantages, disadvantages, or other contrastive/explanatory points.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ir
    -0.07
    ony
    -0.07
     elm
    -0.07
     immense
    -0.07
     engineering
    -0.06
    ensible
    -0.06
     cmp
    -0.06
    .shape
    -0.06
     competitiveness
    -0.06
     покуп
    -0.06
    POSITIVE LOGITS
    ));
    ↵
    ↵
    0.06
    >");
    ↵
    0.06
    @Configuration
    0.06
    >());↵
    0.06
    ---------↵↵
    0.06
    ;\
    0.06
    。(
    0.06
    []}
    0.06
    ']}}</
    0.06
     ESV
    0.06
    Activations Density 0.292%

    No Known Activations