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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55911
    Prev
    Next
    INDEX
    Explanations

    product features descriptions

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on special control tokens (e.g. “<|start_header_id|>”) rather than on regular text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Two
    -0.07
    Saturday
    -0.07
     gaps
    -0.06
    [cur
    -0.06
     trees
    -0.06
    _PF
    -0.06
     deepest
    -0.06
     Myanmar
    -0.06
    Votes
    -0.06
    ")]
    ↵
    -0.06
    POSITIVE LOGITS
     VStack
    0.07
     sebeb
    0.07
     εφαρ
    0.06
    idades
    0.06
     Nẵng
    0.06
    ("/:
    0.06
     Audit
    0.06
     disillusion
    0.06
     ARM
    0.06
     depression
    0.06
    Activations Density 0.051%

    No Known Activations