© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56700
    Prev
    Next
    INDEX
    Explanations

    follow

    np_max-act · gemini-2.0-flash

    The neuron activates on instances of the word “Follow,” e.g. in configuration directives like “FollowSymLinks.”

    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
    Dry
    -0.07
     Dry
    -0.07
    what
    -0.07
     dry
    -0.07
    .trim
    -0.07
    Sizes
    -0.07
    int
    -0.06
    nat
    -0.06
    itr
    -0.06
    price
    -0.06
    POSITIVE LOGITS
     follow
    0.12
     Follow
    0.10
     followers
    0.09
    Follow
    0.09
     follows
    0.09
     following
    0.09
    -follow
    0.08
    follow
    0.08
     Followers
    0.08
    RELATED
    0.08
    Activations Density 0.050%

    No Known Activations