© 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. 16680
    Prev
    Next
    INDEX
    Explanations

    references to international locations and events

    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
     졸
    -0.07
    etto
    -0.07
    uele
    -0.07
    akah
    -0.07
    .hs
    -0.07
    ï¸
    -0.07
    ihn
    -0.07
    ;break
    -0.06
    izona
    -0.06
    mani
    -0.06
    POSITIVE LOGITS
    Specifier
    0.07
    à¸ķร
    0.06
    ¢åįķ
    0.06
    lag
    0.06
    .tc
    0.06
     overseas
    0.06
    lbrace
    0.06
    lacak
    0.05
    emailer
    0.05
     Overse
    0.05
    Activations Density 0.022%

    No Known Activations