© 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. 61337
    Prev
    Next
    INDEX
    Explanations

    specific formatting and organizational structures in text

    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
    utsch
    -0.06
    vester
    -0.06
    lems
    -0.06
     imm
    -0.06
    mán
    -0.06
    ccione
    -0.06
    obus
    -0.06
    kees
    -0.06
     pres
    -0.06
    aa
    -0.05
    POSITIVE LOGITS
    angen
    0.07
    ritel
    0.07
    .scope
    0.07
    anford
    0.07
    .Logic
    0.07
    à¹Ħà¸ĭ
    0.07
     Ùħض
    0.07
    .Scope
    0.07
    polator
    0.07
    Scope
    0.06
    Activations Density 0.015%

    No Known Activations