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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4969
    Prev
    Next
    INDEX
    Explanations

    phrases that express potential actions or intentions

    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
    -alist
    -0.07
    immel
    -0.06
    /Card
    -0.06
    272
    -0.06
    optgroup
    -0.06
    ement
    -0.06
    YW
    -0.06
    273
    -0.06
    ież
    -0.05
    hatt
    -0.05
    POSITIVE LOGITS
    vang
    0.08
    Ñĩи
    0.08
    $MESS
    0.07
    ãĥĭãĥ¼
    0.07
    inges
    0.07
    inging
    0.07
    ÑıÑĩ
    0.07
    ofs
    0.06
     sami
    0.06
    abe
    0.06
    Activations Density 0.005%

    No Known Activations