© 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. 76680
    Prev
    Next
    INDEX
    Explanations

    inquiries or expressions of uncertainty regarding definitions or explanations

    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
     or
    -0.08
     only
    -0.08
     as
    -0.07
     far
    -0.06
     following
    -0.06
     base
    -0.06
     more
    -0.06
    ien
    -0.06
    orp
    -0.06
     absolutely
    -0.06
    POSITIVE LOGITS
    -ÑĤаки
    0.10
    lying
    0.08
    usan
    0.07
    eenth
    0.07
    RootElement
    0.07
    ifiable
    0.07
    ovnÄĽ
    0.07
    unei
    0.07
    oling
    0.07
    -purpose
    0.07
    Activations Density 0.005%

    No Known Activations