© 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. 103742
    Prev
    Next
    INDEX
    Explanations

    phrases that express alternative perspectives or comparisons

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

    Transitional phrases that introduce reformulations or alternative explanations of previously stated information.

    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
    ective
    -0.08
    zin
    -0.07
    291
    -0.06
    quez
    -0.06
    uen
    -0.06
    ï¼
    -0.06
    JA
    -0.06
    avery
    -0.06
    coe
    -0.06
    getObject
    -0.05
    POSITIVE LOGITS
    akin
    0.07
    CRY
    0.07
    ADED
    0.07
    ideon
    0.07
    atrix
    0.07
     simply
    0.06
    LETE
    0.06
    ©
    0.06
    agate
    0.06
    ante
    0.06
    Activations Density 0.025%

    No Known Activations