© 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. 62157
    Prev
    Next
    INDEX
    Explanations

    terms related to technical processes and methodologies in various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical terminology and specialized vocabulary appearing in formal or professional contexts across various domains.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    hdl
    -0.08
    หมาย
    -0.07
    .omg
    -0.07
     Ãľl
    -0.07
    osl
    -0.07
    zm
    -0.07
    еÑĢжав
    -0.07
    enses
    -0.06
    idar
    -0.06
    ÎłÎij
    -0.06
    POSITIVE LOGITS
    illance
    0.07
    OffsetTable
    0.06
     of
    0.06
     Coron
    0.06
    illery
    0.06
    aji
    0.06
    Forest
    0.06
    PointerException
    0.05
    BIG
    0.05
    ote
    0.05
    Activations Density 0.014%

    No Known Activations