© 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. 125405
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or names associated with the term "Rav" or variations thereof

    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
    окÑĥ
    -0.08
    ULE
    -0.08
    nez
    -0.07
    kur
    -0.07
    çª
    -0.07
    IPP
    -0.06
    ROTO
    -0.06
    ARM
    -0.06
     gezocht
    -0.06
    rál
    -0.06
    POSITIVE LOGITS
    put
    0.07
    ieten
    0.07
     pylint
    0.06
    ivos
    0.06
    ãĥªãĥ¼ãĤº
    0.06
    olum
    0.06
    conda
    0.06
     NotificationCenter
    0.06
    lest
    0.06
    nger
    0.06
    Activations Density 0.059%

    No Known Activations