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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126639
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic locations and settings

    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
    ahkan
    -0.07
    ãĤ±ãĥ¼ãĤ¹
    -0.07
    çĸ
    -0.06
    pec
    -0.06
    Tube
    -0.06
    istory
    -0.06
    ede
    -0.06
    emoc
    -0.06
    zia
    -0.06
     Histor
    -0.06
    POSITIVE LOGITS
    ule
    0.07
    ObjectName
    0.06
    .us
    0.06
    ager
    0.06
    mma
    0.06
    -helper
    0.06
    áp
    0.06
     Nicholson
    0.06
    ucker
    0.06
    ieri
    0.06
    Activations Density 0.022%

    No Known Activations