Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4338
    Prev
    Next
    INDEX
    Explanations

    specific dates or months associated with events

    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
    ÑĢÑĸÑı
    -0.08
    oningen
    -0.07
    опÑĢи
    -0.06
    iven
    -0.06
     Ãĸzel
    -0.06
    wap
    -0.06
     graveyard
    -0.06
    éĢģ
    -0.06
    .cz
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
    POSITIVE LOGITS
     
    0.08
    728
    0.07
    27
    0.07
     dil
    0.06
    30
    0.06
    bes
    0.06
    24
    0.06
    reno
    0.06
    26
    0.05
    29
    0.05
    Activations Density 0.036%

    No Known Activations