© 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. 94150
    Prev
    Next
    INDEX
    Explanations

    technical terms related to audio equipment performance and functioning

    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
     Liberation
    -0.07
    iband
    -0.07
    duk
    -0.07
    udu
    -0.07
    ãģŁãĤī
    -0.06
    ISTA
    -0.06
    emey
    -0.06
    QUARE
    -0.06
    andin
    -0.06
    asl
    -0.06
    POSITIVE LOGITS
     safely
    0.09
     acceptable
    0.08
     Safe
    0.07
     tolerated
    0.07
     safe
    0.07
    mai
    0.07
     allowed
    0.07
    _safe
    0.07
     accept
    0.07
     permissible
    0.06
    Activations Density 0.042%

    No Known Activations