© 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. 3988
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and timestamps associated with error messages

    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
     slack
    -0.07
    lse
    -0.07
    lege
    -0.06
    eÄį
    -0.06
    oise
    -0.06
    uye
    -0.06
    ffi
    -0.06
    ุà¸į
    -0.06
    oulos
    -0.06
    itu
    -0.06
    POSITIVE LOGITS
     FileAccess
    0.06
    USTER
    0.06
    inding
    0.06
    croft
    0.06
    obar
    0.06
    [email
    0.06
    standen
    0.06
    Bond
    0.06
    रण
    0.06
    اجÙĩ
    0.05
    Activations Density 0.009%

    No Known Activations