© 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. 118449
    Prev
    Next
    INDEX
    Explanations

    connections between folklore and various aspects of society and culture

    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
     Karlov
    -0.07
    __$
    -0.07
    istra
    -0.07
     faculties
    -0.07
    weit
    -0.07
    dao
    -0.06
    chalk
    -0.06
    ÛĮزÛĮ
    -0.06
    .fm
    -0.06
    å®Į
    -0.06
    POSITIVE LOGITS
    ör
    0.07
    ecta
    0.06
     novel
    0.06
    lijah
    0.06
     patterns
    0.06
    /images
    0.06
     anth
    0.06
     pol
    0.06
     flows
    0.05
     modes
    0.05
    Activations Density 0.041%

    No Known Activations