© 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. 83934
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structural elements

    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
    leur
    -0.08
    ipe
    -0.07
    andi
    -0.07
    nict
    -0.06
    ilities
    -0.06
    hi
    -0.06
    leta
    -0.06
    ll
    -0.06
    ripe
    -0.06
    and
    -0.05
    POSITIVE LOGITS
    arness
    0.08
    Defaults
    0.08
     Picker
    0.08
    .$.
    0.07
    ãĤ¤ãĤº
    0.07
    iddy
    0.07
    ertino
    0.07
    سط
    0.07
    _INITIALIZER
    0.06
    éĻ¢
    0.06
    Activations Density 0.000%

    No Known Activations