© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 120222
    Prev
    Next
    INDEX
    Explanations

    port

    np_max-act · gemini-2.0-flash

    Instances of numeric ports and host:port-like address patterns (IP or hostname followed by ":" and a port).

    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
     Česk
    -0.07
    _cred
    -0.07
     declining
    -0.07
     Quickly
    -0.06
     illnesses
    -0.06
     EH
    -0.06
     purge
    -0.06
    邦
    -0.06
     MULT
    -0.06
    леж
    -0.06
    POSITIVE LOGITS
    (BigInteger
    0.07
    aten
    0.07
    ":"+
    0.06
    iating
    0.06
    assandra
    0.06
     abdom
    0.06
    Thought
    0.06
    важ
    0.06
    časí
    0.06
     uranus
    0.06
    Activations Density 0.008%

    No Known Activations