© 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. 84177
    Prev
    Next
    INDEX
    Explanations

    functions and operations related to database queries and relationships in programming

    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
    <Void
    -0.07
    itals
    -0.06
    156
    -0.06
     exc
    -0.06
     extra
    -0.06
    _VOID
    -0.06
    ely
    -0.06
    wend
    -0.06
     wing
    -0.06
     Tod
    -0.05
    POSITIVE LOGITS
     Given
    0.09
    given
    0.09
    Given
    0.09
     given
    0.08
    (any
    0.08
    _given
    0.08
    ForObject
    0.08
     verilen
    0.08
    (*)(
    0.07
    IVEN
    0.07
    Activations Density 0.155%

    No Known Activations