© 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. 742
    Prev
    Next
    INDEX
    Explanations

    code-related elements or parameters within a programming context

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

    Commas that separate parameters, arguments or values in function calls, method signatures, or initialization lists in programming code.

    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
    owitz
    -0.07
    plug
    -0.06
    ("",
    -0.06
    essen
    -0.06
    _CTL
    -0.06
    oogle
    -0.06
    _TestCase
    -0.06
    inscription
    -0.06
    vault
    -0.06
    mpr
    -0.06
    POSITIVE LOGITS
    å¹ķ
    0.07
    å¹²
    0.06
    elan
    0.06
    183
    0.06
    iza
    0.06
    raquo
    0.06
    GI
    0.06
    ARAM
    0.06
    utors
    0.06
    HEMA
    0.06
    Activations Density 0.032%

    No Known Activations