© 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. 75271
    Prev
    Next
    INDEX
    Explanations

    book publication details and related metadata

    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
    arseille
    -0.07
    ät
    -0.06
    istem
    -0.06
    onis
    -0.06
     Satoshi
    -0.06
    kke
    -0.06
    til
    -0.06
    ethyst
    -0.06
    iar
    -0.06
     bar
    -0.06
    POSITIVE LOGITS
    inery
    0.08
     Harper
    0.07
    _Null
    0.07
     بÙĨدÛĮ
    0.06
    /WebAPI
    0.06
     Penguin
    0.06
    æī£
    0.06
    -wsj
    0.06
    acio
    0.06
    !=(
    0.06
    Activations Density 0.021%

    No Known Activations