© 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. 15-LLAMASCOPE-RES-131K
    11. 89997
    Prev
    Next
    INDEX
    Explanations

    references to media content and announcements related to specific shows or episodes

    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
    athi
    -0.07
    ismet
    -0.07
    ims
    -0.07
    .BorderStyle
    -0.07
    ocale
    -0.06
    rep
    -0.06
    alse
    -0.06
    isté
    -0.06
    yna
    -0.06
     cheek
    -0.06
    POSITIVE LOGITS
     episode
    0.11
     Episode
    0.11
     podcast
    0.10
    Episode
    0.09
    pod
    0.09
     episodes
    0.09
    _pod
    0.08
    -talk
    0.08
    episode
    0.08
     talk
    0.08
    Activations Density 0.132%

    No Known Activations