© 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. 57158
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific evidence and regulatory frameworks

    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
    egin
    -0.07
    LEGRO
    -0.07
     ofType
    -0.06
    lew
    -0.06
    ObjectContext
    -0.06
    tach
    -0.06
    inu
    -0.06
    ego
    -0.06
    lep
    -0.06
    specifier
    -0.06
    POSITIVE LOGITS
     rules
    0.15
     Rules
    0.13
     rule
    0.13
    rules
    0.13
     RULE
    0.13
    è§Ħ
    0.12
    -rule
    0.12
     пÑĢавило
    0.12
     Rule
    0.11
    Rules
    0.11
    Activations Density 0.103%

    No Known Activations