© 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. 118867
    Prev
    Next
    INDEX
    Explanations

    references to specific events or situations involving significant actions or challenges

    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
    icina
    -0.07
    bounce
    -0.06
    ulla
    -0.06
     Depths
    -0.06
    obo
    -0.06
     Tub
    -0.05
    kop
    -0.05
    abad
    -0.05
    61
    -0.05
    ament
    -0.05
    POSITIVE LOGITS
    timeline
    0.09
     background
    0.08
    Timeline
    0.08
     why
    0.07
     reaction
    0.07
    ãģ¾ãĤĭ
    0.07
    background
    0.07
     reactions
    0.07
    referrer
    0.07
    Sortable
    0.07
    Activations Density 0.029%

    No Known Activations