© 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. 75191
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "string" and its variations in a coding context

    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
    MENT
    -0.07
    ãģĬãĤĬ
    -0.07
     serialVersionUID
    -0.07
    /student
    -0.07
    icode
    -0.07
    åħ¶ä¸Ń
    -0.07
    usa
    -0.07
    OwnProperty
    -0.07
    گاÙĩ
    -0.06
    erty
    -0.06
    POSITIVE LOGITS
    .fromCharCode
    0.11
    ified
    0.11
    sWith
    0.09
    (describing
    0.09
    .IsNullOrEmpty
    0.09
    .format
    0.08
    .Format
    0.08
    ently
    0.07
    IFIED
    0.07
     lượng
    0.07
    Activations Density 0.036%

    No Known Activations