© 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. 17-LLAMASCOPE-RES-131K
    11. 125994
    Prev
    Next
    INDEX
    Explanations

    references to sound-related concepts and techniques in immersive media

    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
    icho
    -0.08
     andre
    -0.08
    uler
    -0.07
    niÄį
    -0.07
    hof
    -0.07
    ivement
    -0.07
     meiden
    -0.07
    redi
    -0.07
    wer
    -0.07
    nehmer
    -0.07
    POSITIVE LOGITS
     together
    0.09
     with
    0.08
     elements
    0.08
     disparate
    0.07
     two
    0.07
     forces
    0.07
     expertise
    0.07
     traditional
    0.07
     into
    0.06
     efforts
    0.06
    Activations Density 0.013%

    No Known Activations