© 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. 26978
    Prev
    Next
    INDEX
    Explanations

    filename indicators or metadata associated with music or media reviews

    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
    ifton
    -0.07
    orary
    -0.07
     Fleming
    -0.07
    iar
    -0.07
    itan
    -0.06
     Beck
    -0.06
    ikki
    -0.06
    psilon
    -0.06
    ziel
    -0.05
    essen
    -0.05
    POSITIVE LOGITS
    ayed
    0.07
    άνι
    0.07
    리ëĬĶ
    0.07
    elter
    0.07
    بÙĪاسطة
    0.07
    elib
    0.07
    annies
    0.06
    ãĥ»ãĥ»ãĥ»↵↵
    0.06
    eli
    0.06
    -links
    0.06
    Activations Density 0.005%

    No Known Activations