Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77282
    Prev
    Next
    INDEX
    Explanations

    numeric codes and references typically associated with academic citations or identifiers

    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
     風
    -0.07
    cess
    -0.06
    šť
    -0.06
    porno
    -0.06
    èī¦
    -0.06
    spam
    -0.06
    dum
    -0.06
    isches
    -0.06
    umper
    -0.06
    qi
    -0.06
    POSITIVE LOGITS
    cente
    0.07
    ussen
    0.07
    ì§ĢëıĦ
    0.07
    aroo
    0.07
    åĨ
    0.06
     Carpenter
    0.06
    PELL
    0.06
    feit
    0.06
    PUTE
    0.06
    uct
    0.06
    Activations Density 0.004%

    No Known Activations