© 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. 15288
    Prev
    Next
    INDEX
    Explanations

    instructions for subscribing to news updates

    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
     conc
    -0.06
    hints
    -0.06
    ÑģÑĤиÑĩ
    -0.06
     envelopes
    -0.06
     programs
    -0.06
     transl
    -0.06
    featured
    -0.06
    REATE
    -0.05
    ะ
    -0.05
    xff
    -0.05
    POSITIVE LOGITS
    arda
    0.07
     Graphics
    0.07
    uto
    0.07
    isure
    0.07
    _GENERIC
    0.07
    Crime
    0.07
    IB
    0.07
    arel
    0.07
    acos
    0.07
    aN
    0.06
    Activations Density 0.004%

    No Known Activations