© 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 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. 29310
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate actions or events that unfold in a narrative context

    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
     it
    -0.07
     Readonly
    -0.06
    haust
    -0.06
    بÙĪر
    -0.06
     prime
    -0.06
    w
    -0.06
    hn
    -0.06
     Winds
    -0.06
     its
    -0.05
    orz
    -0.05
    POSITIVE LOGITS
     raining
    0.10
    iner
    0.08
    LEM
    0.08
    chy
    0.08
    alic
    0.07
     incumbent
    0.07
    ty
    0.07
    353
    0.07
    è£ķ
    0.07
    edn
    0.07
    Activations Density 0.040%

    No Known Activations