© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56272
    Prev
    Next
    INDEX
    Explanations

    phrases related to vehicle safety and performance in adverse conditions

    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
    lage
    -0.07
    edula
    -0.07
    iete
    -0.06
     Liberties
    -0.06
    idel
    -0.06
    -tm
    -0.06
    одаÑĢ
    -0.06
    mares
    -0.06
    shade
    -0.06
    ombre
    -0.06
    POSITIVE LOGITS
     Wet
    0.09
     wet
    0.09
     snowy
    0.07
     snow
    0.07
    ivot
    0.07
     uneven
    0.06
     Abram
    0.06
    snow
    0.06
    orrent
    0.06
     icy
    0.06
    Activations Density 0.004%

    No Known Activations