© 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. 61903
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs indicating purpose or intent

    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
    fur
    -0.07
    ough
    -0.06
    inth
    -0.06
    åIJ
    -0.06
    ighbor
    -0.06
     него
    -0.06
    .Misc
    -0.05
    INTR
    -0.05
    urr
    -0.05
    haven
    -0.05
    POSITIVE LOGITS
     create
    0.07
    aland
    0.07
     reel
    0.07
    åĨĬ
    0.06
     produce
    0.06
    auty
    0.06
    hetto
    0.06
    zik
    0.06
    ilon
    0.06
    akra
    0.06
    Activations Density 0.021%

    No Known Activations