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

    Neuronpedia

    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. 11-RESID-POST-AA
    6. 13847
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron is detecting words that occur inside quotation marks (i.e. direct‐speech or quoted passages).

    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
    	Method
    -0.07
    _slave
    -0.07
    ("{
    -0.07
    6
    -0.06
    orrow
    -0.06
    apat
    -0.06
    ενοδο
    -0.06
     دی
    -0.06
    longleftrightarrow
    -0.06
    Nullable
    -0.06
    POSITIVE LOGITS
     dış
    0.06
     reim
    0.06
     unfold
    0.06
     deeply
    0.06
     Bilg
    0.06
    Kim
    0.06
     Tap
    0.06
    elect
    0.06
    扩
    0.06
     colourful
    0.06
    Activations Density 0.061%

    No Known Activations