© 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. 15-LLAMASCOPE-RES-131K
    11. 964
    Prev
    Next
    INDEX
    Explanations

    terms related to death or burial places

    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
    岸
    -0.07
    .Dto
    -0.07
    enton
    -0.07
    endant
    -0.06
    .erb
    -0.06
    feedback
    -0.06
    _DF
    -0.06
    ละ
    -0.06
     cabins
    -0.06
    .Internal
    -0.06
    POSITIVE LOGITS
     hrom
    0.07
     cemetery
    0.07
    osa
    0.07
    lectron
    0.06
    beg
    0.06
    rios
    0.06
    å¢ĵ
    0.06
    neh
    0.06
     Shr
    0.06
    oso
    0.06
    Activations Density 0.002%

    No Known Activations