© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3988
    Prev
    Next
    INDEX
    Explanations

    the name "Cole" and its variations in the text

    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
    ãĥªãĥ³ãĤ¯
    -0.08
    datable
    -0.08
    .fromString
    -0.08
    elope
    -0.07
    iento
    -0.07
    ’ÑĶ
    -0.07
    ãĥ³ãĥĩãĤ£
    -0.07
    izr
    -0.07
    repos
    -0.07
    _NT
    -0.07
    POSITIVE LOGITS
    lla
    0.11
    cción
    0.09
    gio
    0.09
    sterol
    0.08
    fax
    0.08
    brook
    0.08
    man
    0.08
    grave
    0.08
    bourne
    0.07
    ccion
    0.07
    Activations Density 0.002%

    No Known Activations