© 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. 125397
    Prev
    Next
    INDEX
    Explanations

    topics related to community engagement and discussion in a forum setting

    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
    ãĥĭãĥ¼
    -0.07
    ó
    -0.07
    aph
    -0.06
    RequestMethod
    -0.06
    usercontent
    -0.06
    .outputs
    -0.06
    æķ·
    -0.06
    onta
    -0.06
    нÑĸÑĪ
    -0.06
     SMTP
    -0.06
    POSITIVE LOGITS
     general
    0.08
     anything
    0.08
    ugi
    0.07
     Here
    0.07
     Anything
    0.07
    general
    0.07
    anything
    0.06
    Anything
    0.06
    Coder
    0.06
    Here
    0.06
    Activations Density 0.005%

    No Known Activations