© 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. 57249
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting inconsistencies

    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
    cape
    -0.08
     зов
    -0.06
    eb
    -0.06
    found
    -0.06
    urat
    -0.06
    ive
    -0.06
    ces
    -0.05
    ep
    -0.05
    apur
    -0.05
     transit
    -0.05
    POSITIVE LOGITS
    imeline
    0.07
    à¥įयवस
    0.07
    ÑĢиÑģ
    0.07
    XHR
    0.07
    æ²¢
    0.07
    _Control
    0.06
    çĶļ
    0.06
    ÑĭÑģ
    0.06
    ÑĭÑĪ
    0.06
    åįĪ
    0.06
    Activations Density 0.000%

    No Known Activations