© 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. 78783
    Prev
    Next
    INDEX
    Explanations

    concepts related to modeling and inference in biological systems

    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
    cant
    -0.08
    Ø·ØŃ
    -0.07
    ohan
    -0.07
     subrange
    -0.07
    -scalable
    -0.07
     cant
    -0.07
    _VOICE
    -0.07
    adla
    -0.07
    punk
    -0.07
    lÃŃÄį
    -0.07
    POSITIVE LOGITS
     caus
    0.07
     causal
    0.07
     network
    0.06
     Model
    0.06
     model
    0.06
    idd
    0.06
     Jude
    0.06
     Cabinet
    0.06
    fx
    0.06
    ør
    0.06
    Activations Density 0.009%

    No Known Activations