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. 5-LLAMASCOPE-RES-131K
    6. 126258
    Prev
    Next
    INDEX
    Explanations

    occurrences of brand names or company 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
    ↵
    -0.07
     [
    -0.07
     (
    -0.06
    hy
    -0.06
    ...↵
    -0.06
     virtual
    -0.06
     a
    -0.06
     l
    -0.06
     ch
    -0.06
     British
    -0.06
    POSITIVE LOGITS
    _TAC
    0.09
    /DD
    0.09
    ^K
    0.08
    iversit
    0.08
    /Dk
    0.08
    <source
    0.08
     predecess
    0.08
    Mutable
    0.08
    /Library
    0.08
    utow
    0.08
    Activations Density 0.006%

    No Known Activations