© 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. 57607
    Prev
    Next
    INDEX
    Explanations

    references to causes or effects related to actions or situations

    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
    ti
    -0.08
    ize
    -0.08
    rei
    -0.08
    jam
    -0.07
    re
    -0.07
    the
    -0.07
    reg
    -0.07
     Burr
    -0.07
    ت
    -0.07
    cken
    -0.07
    POSITIVE LOGITS
    lessly
    0.10
     cél
    0.09
    -effect
    0.09
    ëģĶ
    0.08
    illard
    0.08
     cele
    0.08
    ño
    0.07
    ños
    0.07
    ps
    0.07
    anova
    0.07
    Activations Density 0.027%

    No Known Activations