© 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. 60656
    Prev
    Next
    INDEX
    Explanations

    descriptors related to someone's personality or character traits

    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
    åde
    -0.09
    łéĻ¤
    -0.09
    OffsetTable
    -0.08
    CodeAt
    -0.08
    .scalablytyped
    -0.07
    æ£
    -0.07
    Ŀ¼
    -0.07
    GuidId
    -0.07
    .LENGTH
    -0.07
    ScrollIndicator
    -0.07
    POSITIVE LOGITS
    виÑĤ
    0.06
    INST
    0.06
     swe
    0.06
    ì§Ħ
    0.06
     middle
    0.06
     inj
    0.05
    lyph
    0.05
     same
    0.05
    apon
    0.05
    _CB
    0.05
    Activations Density 0.000%

    No Known Activations