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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 96146
    Prev
    Next
    INDEX
    Explanations

    discussions about political candidacy and elections

    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
    urt
    -0.06
    iao
    -0.06
    uxt
    -0.06
     Sheldon
    -0.06
    amarin
    -0.06
    ils
    -0.06
    aud
    -0.06
    ниÑĨÑĤва
    -0.06
    our
    -0.05
    intl
    -0.05
    POSITIVE LOGITS
     ÑģкладÑĸ
    0.07
    ;base
    0.07
     CHIP
    0.07
    MBED
    0.07
     {{--<
    0.07
    HIR
    0.07
    Ìģt
    0.07
    æº
    0.07
    /GPL
    0.07
    Invocation
    0.06
    Activations Density 0.002%

    No Known Activations