© 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. 27443
    Prev
    Next
    INDEX
    Explanations

    terms related to violations and constraints

    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
    ileo
    -0.08
    eled
    -0.08
    eza
    -0.08
    orial
    -0.08
    å£Ĭ
    -0.08
    _fu
    -0.07
    ãĤ«ãĥĨ
    -0.07
    å¼ķãģį
    -0.07
    .scalablytyped
    -0.07
    ãĥĩãĤ£ãĤ¢
    -0.07
    POSITIVE LOGITS
    ative
    0.06
    363
    0.06
    é
    0.06
    572
    0.06
    /v
    0.06
    acco
    0.06
    arb
    0.06
    æĮģ
    0.06
    .TYPE
    0.06
    _gold
    0.06
    Activations Density 0.008%

    No Known Activations