© 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. 118579
    Prev
    Next
    INDEX
    Explanations

    years mentioned in the text

    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
    thal
    -0.07
     agency
    -0.06
    ogo
    -0.06
    æ°ı
    -0.06
    nnen
    -0.06
    uala
    -0.05
     exercising
    -0.05
     karak
    -0.05
    TEM
    -0.05
    245
    -0.05
    POSITIVE LOGITS
    berger
    0.07
    ResponseStatus
    0.07
     gint
    0.07
    andest
    0.07
    antino
    0.07
     neur
    0.06
    rak
    0.06
    LBL
    0.06
    LF
    0.06
    /fw
    0.06
    Activations Density 0.012%

    No Known Activations