© 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. 75279
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal development and collective action towards achieving goals

    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
    allen
    -0.07
    .nlm
    -0.07
     Guid
    -0.07
    DEFINED
    -0.07
    aman
    -0.06
    usercontent
    -0.06
    ahlen
    -0.06
    chod
    -0.06
     eigenen
    -0.06
     fate
    -0.06
    POSITIVE LOGITS
     starters
    0.10
     step
    0.10
     start
    0.10
     begin
    0.10
     beginning
    0.09
     initial
    0.08
     begins
    0.08
     progress
    0.08
     partial
    0.08
     Step
    0.08
    Activations Density 0.052%

    No Known Activations