Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96030
    Prev
    Next
    INDEX
    Explanations

    positive adjectives that describe quality and aesthetics

    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
    ÑıÑģÑĮ
    -0.06
    rts
    -0.06
    izontal
    -0.06
    /Peak
    -0.06
    antas
    -0.06
    NetBar
    -0.06
    316
    -0.06
    ctest
    -0.06
    ESSAGES
    -0.06
    ázd
    -0.06
    POSITIVE LOGITS
    abil
    0.08
     reput
    0.07
    çĪŃ
    0.07
     ëĴ
    0.07
    amac
    0.07
    phin
    0.07
    ajar
    0.07
    ãĥ©ãĥ³ãĥī
    0.06
     Cloth
    0.06
    ption
    0.06
    Activations Density 0.048%

    No Known Activations