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. 95987
    Prev
    Next
    INDEX
    Explanations

    references to Mars in various contexts

    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
    erver
    -0.08
    artner
    -0.07
    akin
    -0.07
    emin
    -0.07
    skirts
    -0.07
    eated
    -0.07
    taire
    -0.07
    çİĩ
    -0.07
    ond
    -0.07
    tit
    -0.06
    POSITIVE LOGITS
    баÑĩ
    0.08
    quee
    0.07
    еÑĦ
    0.07
    TokenType
    0.07
    .Flag
    0.06
     ÐĹем
    0.06
    quel
    0.06
     Lucky
    0.06
    ượt
    0.06
    uell
    0.06
    Activations Density 0.006%

    No Known Activations