© 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. 106459
    Prev
    Next
    INDEX
    Explanations

    references to democratic rights and freedoms

    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
    erland
    -0.08
    monds
    -0.08
    kees
    -0.08
    ç´
    -0.08
    contres
    -0.08
    strom
    -0.08
    rix
    -0.07
     CommandType
    -0.07
    ritch
    -0.07
    atus
    -0.07
    POSITIVE LOGITS
     freely
    0.12
     Fre
    0.07
     aerial
    0.07
     expression
    0.06
     Schwartz
    0.06
     FRE
    0.06
     openly
    0.06
    328
    0.06
    Fre
    0.05
     Freeman
    0.05
    Activations Density 0.023%

    No Known Activations