© 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. 15-LLAMASCOPE-RES-131K
    6. 61746
    Prev
    Next
    INDEX
    Explanations

    structured data, particularly in the format of JSON

    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
    lege
    -0.07
    /or
    -0.06
    ocre
    -0.06
    voy
    -0.06
    vore
    -0.06
     Mol
    -0.06
     original
    -0.06
    vais
    -0.06
    ende
    -0.05
    ervers
    -0.05
    POSITIVE LOGITS
    Parms
    0.08
    /umd
    0.08
    #ac
    0.08
    #ab
    0.08
    .CG
    0.07
    ẩn
    0.07
    icens
    0.07
    ãĥ³ãĥĶ
    0.07
     hava
    0.07
    .Focused
    0.07
    Activations Density 0.003%

    No Known Activations