© 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. 57530
    Prev
    Next
    INDEX
    Explanations

    instances of inclusion and collaboration across various contexts

    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
    lav
    -0.07
    asma
    -0.07
     Thief
    -0.06
    abcd
    -0.06
    759
    -0.06
    uras
    -0.06
     away
    -0.06
     Leicester
    -0.06
    379
    -0.06
     Wiki
    -0.06
    POSITIVE LOGITS
     into
    0.10
    into
    0.10
     vÃło
    0.09
     Into
    0.08
    Into
    0.08
     nelle
    0.08
    à¹ĥà¸Ļà¸ģาร
    0.08
     INTO
    0.08
    _into
    0.08
     trong
    0.08
    Activations Density 0.085%

    No Known Activations