© 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. 1157
    Prev
    Next
    INDEX
    Explanations

    programming or technical details involving serialization or data structures

    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
    -0.07
    âī¡
    -0.07
    аÑĤкÑĥ
    -0.07
     Aires
    -0.06
    nts
    -0.06
    sing
    -0.06
    á»Ļng
    -0.06
    APT
    -0.06
    dling
    -0.06
    ìĻ
    -0.06
    POSITIVE LOGITS
     sublic
    0.07
    /includes
    0.06
    sterol
    0.06
    xmm
    0.06
    asti
    0.06
    icode
    0.06
    lava
    0.06
    semble
    0.06
     SplashScreen
    0.06
     carte
    0.06
    Activations Density 0.014%

    No Known Activations