© 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. 40853
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to audio and video data handling

    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
    inker
    -0.08
    /boot
    -0.07
    .writerow
    -0.06
     standoff
    -0.06
    ale
    -0.06
    ored
    -0.06
    ignal
    -0.06
    755
    -0.06
    /Getty
    -0.06
    esa
    -0.06
    POSITIVE LOGITS
     video
    0.10
    brtc
    0.08
    video
    0.08
     Video
    0.07
     NAT
    0.07
    è§Ĩé¢ij
    0.07
    rtc
    0.07
    mute
    0.07
     audio
    0.06
     speech
    0.06
    Activations Density 0.030%

    No Known Activations