© 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. 125488
    Prev
    Next
    INDEX
    Explanations

    genres and themes related to crime and thrillers

    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
    uzey
    -0.07
    /lic
    -0.07
    çĢ¬
    -0.06
     Rosen
    -0.06
     (?)
    -0.06
     Gill
    -0.06
    essel
    -0.06
     Hass
    -0.05
     Mans
    -0.05
    lick
    -0.05
    POSITIVE LOGITS
     genre
    0.09
     literature
    0.08
    tember
    0.08
    Configurer
    0.08
    -kind
    0.07
    apol
    0.07
     Benchmark
    0.07
    iscal
    0.07
    /fw
    0.06
    -Sah
    0.06
    Activations Density 0.021%

    No Known Activations