© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4330
    Prev
    Next
    INDEX
    Explanations

    newly introduced or referenced entities in a text

    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
     Agencies
    -0.07
     Associates
    -0.06
    ousse
    -0.06
    ancer
    -0.06
     Committees
    -0.06
    utter
    -0.06
    acher
    -0.06
    ollen
    -0.06
     Embassy
    -0.06
    ãĥ³ãĤ¯
    -0.06
    POSITIVE LOGITS
     director
    0.23
     CEO
    0.23
     chief
    0.22
     Director
    0.21
     president
    0.20
     head
    0.19
     Chief
    0.19
    CEO
    0.19
    director
    0.19
     manager
    0.19
    Activations Density 0.009%

    No Known Activations