© 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. 15-LLAMASCOPE-RES-131K
    11. 62159
    Prev
    Next
    INDEX
    Explanations

    elements related to research and scientific methodologies

    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
    ãĥ³ãĥĶ
    -0.07
    [^
    -0.07
    Spl
    -0.07
    Äįet
    -0.07
     Spl
    -0.07
    hammad
    -0.07
    #ac
    -0.06
    Ñĥков
    -0.06
    lernen
    -0.06
    è·ĿéĽ¢
    -0.06
    POSITIVE LOGITS
     \
    0.08
    erm
    0.07
     accessor
    0.07
    \
    0.06
    REATE
    0.06
    ivil
    0.06
    ál
    0.06
     additionally
    0.06
    ÅĻ
    0.05
    Getter
    0.05
    Activations Density 2.763%

    No Known Activations