© 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. 84078
    Prev
    Next
    INDEX
    Explanations

    elements related to file configuration and plugin setup instructions

    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
    fi
    -0.10
    zell
    -0.08
    corner
    -0.07
    zd
    -0.07
     stil
    -0.07
     Computes
    -0.07
     corner
    -0.07
    åłĤ
    -0.07
     èĭ¥
    -0.07
    Ïħνα
    -0.06
    POSITIVE LOGITS
     Responsible
    0.08
     responsible
    0.08
     basically
    0.07
     responsable
    0.06
    longleftrightarrow
    0.06
     must
    0.06
     MUST
    0.06
     kez
    0.06
    Decl
    0.06
    isOk
    0.06
    Activations Density 0.031%

    No Known Activations