© 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. 15-LLAMASCOPE-RES-131K
    11. 103877
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurement or evaluation

    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
    /Internal
    -0.07
    OffsetTable
    -0.07
     yiy
    -0.07
     addCriterion
    -0.06
    nothrow
    -0.06
    rones
    -0.06
    .appspot
    -0.06
    .ExecuteReader
    -0.06
    HeaderCode
    -0.06
    498
    -0.06
    POSITIVE LOGITS
    abin
    0.06
    otte
    0.06
    anche
    0.06
     symbolism
    0.06
    ĽĦ
    0.06
    esini
    0.06
    \_
    0.06
     electronics
    0.06
     Muscle
    0.06
    olin
    0.06
    Activations Density 0.000%

    No Known Activations