© 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. 40121
    Prev
    Next
    INDEX
    Explanations

    coding constructs related to status checks and constraints

    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
    .scalablytyped
    -0.09
    hee
    -0.07
    rott
    -0.07
    )?$
    -0.07
    instead
    -0.07
    weis
    -0.07
    LocalizedString
    -0.06
    æ®Ĭ
    -0.06
    agn
    -0.06
     Baum
    -0.06
    POSITIVE LOGITS
    èĩ³å°ij
    0.07
    egrity
    0.07
    ovit
    0.06
    gado
    0.06
    ata
    0.06
     atleast
    0.06
    inde
    0.06
    gart
    0.05
    sel
    0.05
    ?p
    0.05
    Activations Density 0.025%

    No Known Activations