© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61236
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "things."

    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
    PÅĻed
    -0.07
    aklı
    -0.07
    ec
    -0.06
    endon
    -0.06
    PÅĻi
    -0.06
    owned
    -0.06
    inces
    -0.06
    aging
    -0.06
    utschen
    -0.06
    بÙĪØ¯
    -0.06
    POSITIVE LOGITS
    exels
    0.06
    cha
    0.06
    ç´
    0.06
     Sesso
    0.06
    afb
    0.06
    _perms
    0.06
    -Smith
    0.06
    annes
    0.06
    ichten
    0.06
    atur
    0.06
    Activations Density 0.011%

    No Known Activations