© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 62201
    Prev
    Next
    INDEX
    Explanations

    linguistic structures that imply evaluation or classification of subjects

    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
    ester
    -0.06
    ee
    -0.06
    fi
    -0.06
    ce
    -0.06
    uy
    -0.06
    acock
    -0.06
     Disp
    -0.06
    è¶ħè¿ĩ
    -0.06
    317
    -0.05
    quist
    -0.05
    POSITIVE LOGITS
    aign
    0.08
    cribe
    0.08
    нен
    0.08
    upertino
    0.08
    enance
    0.07
    ruba
    0.07
    gnore
    0.07
    utenberg
    0.07
    пÑĢиклад
    0.07
    atham
    0.07
    Activations Density 0.026%

    No Known Activations