© 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. 5384
    Prev
    Next
    INDEX
    Explanations

    phrases related to naming and identity

    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
    _INF
    -0.07
     Ashton
    -0.07
    ichert
    -0.07
    еÑĢеж
    -0.06
    ège
    -0.06
    ï¼»
    -0.06
    Ïĥμο
    -0.06
    Ä
    -0.06
    unk
    -0.06
    emploi
    -0.06
    POSITIVE LOGITS
    625
    0.07
    ihar
    0.06
    plorer
    0.06
    ¯ÃĤ
    0.06
    Ŀi
    0.06
    627
    0.06
    Ŀ
    0.06
    encil
    0.06
    668
    0.06
    rib
    0.06
    Activations Density 0.002%

    No Known Activations