Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95790
    Prev
    Next
    INDEX
    Explanations

    terms indicating values or settings related to coding and program variables

    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
     varying
    -0.06
     Gent
    -0.06
    nist
    -0.06
     chac
    -0.06
     pre
    -0.06
    vail
    -0.06
    sole
    -0.06
     ÑģобоÑİ
    -0.06
    act
    -0.06
    kir
    -0.06
    POSITIVE LOGITS
    .HttpSession
    0.07
    пеÑĩ
    0.07
    ccione
    0.07
    etros
    0.07
    ulers
    0.06
    lund
    0.06
    owell
    0.06
     è¢
    0.06
    ajan
    0.06
    azer
    0.06
    Activations Density 0.001%

    No Known Activations