© 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. 87792
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or entity associated with the name "Fre" 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
    amm
    -0.08
    itia
    -0.07
    ored
    -0.07
    ryan
    -0.07
    649
    -0.07
    Ïĥμα
    -0.06
    res
    -0.06
    ooth
    -0.06
    ry
    -0.06
    ntax
    -0.06
    POSITIVE LOGITS
    QUENCY
    0.08
    ddie
    0.08
    mlin
    0.07
    amework
    0.07
    quent
    0.07
    ibur
    0.07
    lse
    0.07
     âĹĦ
    0.07
    ewe
    0.07
    -fw
    0.07
    Activations Density 0.007%

    No Known Activations