© 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. 15-LLAMASCOPE-RES-131K
    11. 104098
    Prev
    Next
    INDEX
    Explanations

    references to locations and directions

    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
    gw
    -0.07
    ียà¸ļ
    -0.07
    flip
    -0.06
    shaw
    -0.06
    adaki
    -0.06
     hal
    -0.06
    ήÏĤ
    -0.06
    anne
    -0.06
    below
    -0.06
    @qq
    -0.06
    POSITIVE LOGITS
    ulumi
    0.08
    çİ°åľº
    0.07
     Ú¯ÙĦ
    0.06
    esture
    0.06
     Exclusive
    0.06
    /signup
    0.06
    _exclude
    0.06
    NAL
    0.06
     omas
    0.06
    arsity
    0.06
    Activations Density 0.001%

    No Known Activations