© 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. 62148
    Prev
    Next
    INDEX
    Explanations

    references to articles, publications, or identifiers related to specific works or individuals

    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
    pt
    -0.07
     site
    -0.06
     em
    -0.06
    PT
    -0.06
     se
    -0.06
     distributions
    -0.06
     bypass
    -0.06
     sites
    -0.06
     disease
    -0.05
    atto
    -0.05
    POSITIVE LOGITS
    надлеж
    0.08
    ï¼Ń
    0.08
     Ñģигн
    0.08
     voks
    0.08
    волÑı
    0.08
    krv
    0.07
    ","\
    0.07
    ¯¸
    0.07
    usk
    0.07
    ÑĨеÑģ
    0.07
    Activations Density 0.003%

    No Known Activations