Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96015
    Prev
    Next
    INDEX
    Explanations

    items related to protective coverings and maintenance products

    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
    AWS
    -0.07
     Curtis
    -0.06
    unge
    -0.06
     Bon
    -0.06
    ãĤ·ãĤ§
    -0.06
    pj
    -0.06
    stellung
    -0.06
    rend
    -0.06
    UCKET
    -0.06
    æŃ´
    -0.05
    POSITIVE LOGITS
    .sponge
    0.09
    bach
    0.07
    å´İ
    0.07
    TECT
    0.07
    ysi
    0.07
    -END
    0.07
    STRU
    0.07
    .bukkit
    0.06
    -LAST
    0.06
    ,proto
    0.06
    Activations Density 0.007%

    No Known Activations