© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3984
    Prev
    Next
    INDEX
    Explanations

    complex and multidimensional characters and their diverse traits in narratives

    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
    ä¼´
    -0.07
    asu
    -0.07
    óng
    -0.07
     Karlov
    -0.07
    ktor
    -0.07
    statt
    -0.07
    PTY
    -0.06
    agg
    -0.06
     Alg
    -0.06
    isure
    -0.06
    POSITIVE LOGITS
     initially
    0.14
     until
    0.13
    until
    0.11
     Initially
    0.11
    Initially
    0.10
     Until
    0.10
    initial
    0.09
    Until
    0.09
     initial
    0.09
     except
    0.09
    Activations Density 0.058%

    No Known Activations