© 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. 17-LLAMASCOPE-RES-131K
    11. 129990
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups mentioned in contexts of action or influence

    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
     Ñģама
    -0.09
    //{{
    -0.08
    .scalablytyped
    -0.08
    YE
    -0.08
    ÑĢава
    -0.07
    ủi
    -0.07
    ãĤ¤ãĥ³
    -0.07
    _MANY
    -0.07
    statt
    -0.07
    .Ui
    -0.07
    POSITIVE LOGITS
     otherwise
    0.08
     themselves
    0.08
     frequent
    0.07
     whose
    0.06
     marginal
    0.06
     rem
    0.06
     or
    0.06
    otherwise
    0.06
     want
    0.06
     chance
    0.06
    Activations Density 0.040%

    No Known Activations