© 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. 15-LLAMASCOPE-RES-131K
    6. 61912
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    âĢŀA
    -0.06
    ANDLE
    -0.06
    gere
    -0.06
     yyn
    -0.06
    ropped
    -0.06
    âĢŀM
    -0.06
    ư
    -0.06
    -ed
    -0.05
    ÑĪки
    -0.05
    енÑģ
    -0.05
    POSITIVE LOGITS
    ownt
    0.07
    stav
    0.07
    hev
    0.07
    idel
    0.07
    IAS
    0.06
    abant
    0.06
    strand
    0.06
    ighter
    0.06
     Territory
    0.06
    unes
    0.06
    Activations Density 0.000%

    No Known Activations