© 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. 84682
    Prev
    Next
    INDEX
    Explanations

    references to critically acclaimed or award-nominated films

    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
    оÑĢаз
    -0.06
    _customize
    -0.06
    _effect
    -0.06
     SHALL
    -0.06
    CSI
    -0.06
    nan
    -0.06
    ?}",
    -0.06
    _processors
    -0.06
    _USED
    -0.05
    icens
    -0.05
    POSITIVE LOGITS
     budget
    0.07
    .FLAG
    0.07
    apol
    0.07
    Budget
    0.07
    anitize
    0.07
     Budget
    0.06
     à¤¬à¤ľ
    0.06
    budget
    0.06
    urat
    0.06
    Exited
    0.06
    Activations Density 0.027%

    No Known Activations