© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94177
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Carol."

    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
    yon
    -0.07
    ENO
    -0.07
    sgi
    -0.07
    oxy
    -0.07
    ugg
    -0.06
    etz
    -0.06
    alic
    -0.06
    iones
    -0.06
    ugin
    -0.06
    {{{
    -0.06
    POSITIVE LOGITS
    åħĥ
    0.07
    inear
    0.07
    ibe
    0.06
     Matth
    0.06
    AC
    0.06
    uido
    0.06
     springs
    0.06
    uffy
    0.06
    le
    0.06
    ACHI
    0.06
    Activations Density 0.004%

    No Known Activations