© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61447
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and their affiliations

    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
    olit
    -0.08
    icus
    -0.07
     Levine
    -0.07
    á»§
    -0.06
    opoulos
    -0.06
    ãģĵãģĨ
    -0.06
    XD
    -0.06
    zman
    -0.06
    allis
    -0.06
    untary
    -0.06
    POSITIVE LOGITS
    asaki
    0.06
    afil
    0.06
    paper
    0.06
    leÅŁik
    0.06
     ÑĩÑĥж
    0.06
    égor
    0.06
    ozilla
    0.06
    580
    0.06
    竾
    0.06
    ComputedStyle
    0.06
    Activations Density 0.079%

    No Known Activations