© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106982
    Prev
    Next
    INDEX
    Explanations

    colons followed by context or significant information

    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
    jie
    -0.07
    ÑĤÑİ
    -0.07
    agh
    -0.06
    опол
    -0.06
    ÑģилÑĮ
    -0.06
    веÑĢд
    -0.06
    itch
    -0.06
    abble
    -0.06
    uard
    -0.06
    ictim
    -0.06
    POSITIVE LOGITS
    kowski
    0.08
    readcr
    0.07
     admin
    0.06
    tas
    0.06
    onymous
    0.06
     ste
    0.06
    logan
    0.06
    gone
    0.06
    SDL
    0.06
    º«
    0.06
    Activations Density 0.006%

    No Known Activations