© 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. 119550
    Prev
    Next
    INDEX
    Explanations

    tabular data with statistical or quantitative information

    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
    ÑĢд
    -0.06
    reau
    -0.06
    inho
    -0.05
    caled
    -0.05
    etty
    -0.05
    azar
    -0.05
    antis
    -0.05
     oci
    -0.05
    ombs
    -0.05
     displ
    -0.05
    POSITIVE LOGITS
    eya
    0.07
    IQ
    0.07
    λαν
    0.07
    дина
    0.07
    ãĥ¼ãĥĨãĤ£
    0.06
     Ùħات
    0.06
    .TryParse
    0.06
     EÅŁ
    0.06
    olis
    0.06
    inventory
    0.06
    Activations Density 0.006%

    No Known Activations