© 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. 79815
    Prev
    Next
    INDEX
    Explanations

    information related to ice block creation and management

    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
    ERG
    -0.07
    ove
    -0.07
    .light
    -0.06
    breadcrumb
    -0.06
     lighting
    -0.06
     Ú©ÙĪÚĨ
    -0.06
     Lighting
    -0.06
    chner
    -0.06
     IGN
    -0.06
    лоб
    -0.06
    POSITIVE LOGITS
     ice
    0.10
     Ice
    0.09
     freezer
    0.08
     Frozen
    0.08
    Ice
    0.07
    Vectorizer
    0.07
     freezing
    0.07
     froze
    0.07
    Frozen
    0.07
     frozen
    0.07
    Activations Density 0.009%

    No Known Activations