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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1064
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong desires or demands

    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
    zure
    -0.07
     ont
    -0.07
    -alist
    -0.06
    acam
    -0.06
    ont
    -0.06
    freq
    -0.06
     Terminal
    -0.06
    icos
    -0.06
    ativity
    -0.06
     Bbw
    -0.06
    POSITIVE LOGITS
    ppe
    0.07
    field
    0.07
    efon
    0.06
    ylvania
    0.06
    istique
    0.06
    .lu
    0.06
    _mk
    0.06
    .Require
    0.06
    kinson
    0.06
    ãĥ¼ãĤº
    0.06
    Activations Density 0.220%

    No Known Activations