© 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. 15-LLAMASCOPE-RES-131K
    11. 26964
    Prev
    Next
    INDEX
    Explanations

    elements of character relationships and interpersonal dynamics

    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
    unma
    -0.09
    á»ijc
    -0.08
    ughs
    -0.08
    hiba
    -0.08
    lemn
    -0.08
    entar
    -0.08
     æ¤
    -0.08
    icas
    -0.07
    ãģĵãĤĵãģ«
    -0.07
    undi
    -0.07
    POSITIVE LOGITS
     break
    0.07
     breaks
    0.06
     and
    0.06
     sponsored
    0.06
     alone
    0.06
     breakout
    0.06
     representative
    0.06
     freedom
    0.06
     fellow
    0.06
     breaking
    0.06
    Activations Density 0.007%

    No Known Activations