© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70985
    Prev
    Next
    INDEX
    Explanations

    references to financial and administrative processes and contact information

    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
    alic
    -0.07
    aland
    -0.06
    öh
    -0.06
     neust
    -0.06
    rev
    -0.06
    als
    -0.06
    amel
    -0.06
    un
    -0.06
    ekl
    -0.06
    oyer
    -0.06
    POSITIVE LOGITS
    ulings
    0.07
    CJK
    0.07
    bcm
    0.07
    ç½ijåĿĢ
    0.07
     listed
    0.07
    æĪĸ
    0.07
     or
    0.07
    nearest
    0.07
    λλι
    0.06
     nearest
    0.06
    Activations Density 0.016%

    No Known Activations