© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3598
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an address or a call to action for a specific individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cob
    -0.06
    ension
    -0.06
     Kor
    -0.06
    riend
    -0.06
    ÙİÙĩ
    -0.06
     nouve
    -0.06
     Walton
    -0.05
    artic
    -0.05
    arts
    -0.05
    åıĤ
    -0.05
    POSITIVE LOGITS
    éŁ¿
    0.08
    _saida
    0.07
    someone
    0.07
    tero
    0.07
    .Formatter
    0.07
    ostel
    0.07
    jac
    0.07
    .AutoComplete
    0.07
    jom
    0.07
    urry
    0.06
    Activations Density 0.000%

    No Known Activations