© 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 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. 17-LLAMASCOPE-RES-131K
    11. 58528
    Prev
    Next
    INDEX
    Explanations

    terms related to the benefits, risks, and specifications of different subjects or technologies

    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
     Gros
    -0.08
    PROTO
    -0.07
    /epl
    -0.07
    ãĥ³ãĥķ
    -0.07
    ãĥ³ãĥĢ
    -0.07
    ฤ
    -0.07
    ostel
    -0.07
     Twice
    -0.07
    /inet
    -0.07
    äºŃ
    -0.07
    POSITIVE LOGITS
    Âł
    0.06
     rh
    0.06
     fo
    0.06
    yat
    0.06
    arta
    0.05
    lista
    0.05
    bsite
    0.05
     of
    0.05
     points
    0.05
    å¦Ĥä¸ĭ
    0.05
    Activations Density 0.035%

    No Known Activations