© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77398
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and computing systems

    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
    /use
    -0.07
    maj
    -0.06
     scav
    -0.06
     gre
    -0.06
    407
    -0.06
    evin
    -0.06
    gre
    -0.06
    ry
    -0.06
    requ
    -0.06
    gue
    -0.06
    POSITIVE LOGITS
    mun
    0.07
    lico
    0.07
    odyn
    0.07
    æijĩ
    0.07
    âĢĮسÛĮ
    0.07
    datatype
    0.07
    ((__
    0.07
    efined
    0.07
    ernen
    0.06
    оÑĢалÑĮ
    0.06
    Activations Density 0.099%

    No Known Activations