© 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. 125177
    Prev
    Next
    INDEX
    Explanations

    websites or sources of information, particularly news and statistics

    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
    ann
    -0.06
    yst
    -0.06
     micro
    -0.06
    arming
    -0.06
    ple
    -0.06
    pl
    -0.06
    avel
    -0.06
     VS
    -0.05
    uhl
    -0.05
     AS
    -0.05
    POSITIVE LOGITS
    :↵↵
    0.12
    ":↵
    0.11
    :↵
    0.11
    :↵↵↵
    0.10
    ):↵
    0.10
     ):↵
    0.10
    "):↵
    0.10
    ':↵
    0.10
    :č↵
    0.10
    ]:↵
    0.10
    Activations Density 0.014%

    No Known Activations