© 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. 77414
    Prev
    Next
    INDEX
    Explanations

    repeated phrases emphasizing similarity

    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
    jeme
    -0.07
    quo
    -0.06
    rani
    -0.06
    asma
    -0.06
     also
    -0.06
     own
    -0.06
    178
    -0.06
    arena
    -0.06
    at
    -0.06
    icity
    -0.06
    POSITIVE LOGITS
     kind
    0.09
    -sex
    0.08
     sort
    0.08
     kinds
    0.08
    unma
    0.07
     sorts
    0.07
    ãĤĪãģĨãģª
    0.07
    MEDIA
    0.07
    avig
    0.07
    PRESS
    0.07
    Activations Density 0.019%

    No Known Activations