© 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. 28938
    Prev
    Next
    INDEX
    Explanations

    alerts or notifications related to system messages or errors

    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
    olin
    -0.07
    achel
    -0.06
     actionTypes
    -0.06
     --
    -0.06
     —
    -0.06
     Morm
    -0.06
     chem
    -0.06
    -trans
    -0.06
     jug
    -0.06
    auth
    -0.05
    POSITIVE LOGITS
    ÙĪارÙĩ
    0.07
    ãĥĨãĥ«
    0.07
    nova
    0.07
    :\/\/
    0.06
    lename
    0.06
     ano
    0.06
    ofday
    0.06
    Pipeline
    0.06
    (crate
    0.06
     Tweet
    0.06
    Activations Density 0.000%

    No Known Activations