© 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. 76204
    Prev
    Next
    INDEX
    Explanations

    podcast episode titles and metadata

    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
     Ñģоп
    -0.07
    opp
    -0.07
    jez
    -0.06
    ieri
    -0.06
    etc
    -0.06
     Ù¾ÛĮÚĨ
    -0.06
    .fi
    -0.06
    lead
    -0.06
    appe
    -0.06
    iffe
    -0.06
    POSITIVE LOGITS
     Episode
    0.13
     episode
    0.13
    episode
    0.12
    Episode
    0.11
     episodes
    0.11
     podcast
    0.11
    _episode
    0.10
    pod
    0.09
    isode
    0.09
     Episodes
    0.09
    Activations Density 0.025%

    No Known Activations