© 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. 84091
    Prev
    Next
    INDEX
    Explanations

    expressions of purpose and underlying motivations

    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
    ç´
    -0.06
    lÃŃ
    -0.06
    JECTION
    -0.06
    ç¹Ķ
    -0.06
    Pink
    -0.06
    exampleInputEmail
    -0.06
    ê±´
    -0.06
    oci
    -0.06
    جÙĩ
    -0.06
    ij
    -0.06
    POSITIVE LOGITS
    (s
    0.08
    inite
    0.07
    annel
    0.07
    ा:
    0.07
    IODevice
    0.06
    :
    0.06
    rát
    0.06
    ries
    0.06
    284
    0.06
    ermal
    0.06
    Activations Density 0.004%

    No Known Activations