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. 95934
    Prev
    Next
    INDEX
    Explanations

    numeric data and identifiers related to data sets

    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
    ule
    -0.07
    agher
    -0.06
    ObjectContext
    -0.06
    utton
    -0.06
    duk
    -0.06
    .ws
    -0.06
     seldom
    -0.06
    .synthetic
    -0.06
     rarely
    -0.06
    owl
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥĦ
    0.07
     åıĮ线
    0.07
    @testable
    0.07
    utilus
    0.06
     Riot
    0.06
    iero
    0.06
    leared
    0.06
    å£
    0.06
    edd
    0.06
    ãĥªãĤ«
    0.06
    Activations Density 0.001%

    No Known Activations