© 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. 29608
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Rose" 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
    resse
    -0.07
    ropolis
    -0.07
    Forgery
    -0.07
    غاÙĨ
    -0.06
    uby
    -0.06
     prescribed
    -0.06
    upa
    -0.06
    uper
    -0.06
    ress
    -0.06
    ersion
    -0.06
    POSITIVE LOGITS
    mary
    0.14
    bud
    0.10
    velt
    0.09
    /ros
    0.09
    anna
    0.08
    æŀĿ
    0.08
    MARY
    0.08
    holm
    0.08
    cco
    0.07
    Ľ°
    0.07
    Activations Density 0.010%

    No Known Activations