© 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. 75117
    Prev
    Next
    INDEX
    Explanations

    questions and discussions about marketing strategies aimed at specific demographics

    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
    zin
    -0.07
     Fury
    -0.06
    umber
    -0.06
    uin
    -0.06
    edor
    -0.06
    qq
    -0.06
    bjerg
    -0.06
    ilde
    -0.06
     Niet
    -0.06
    mong
    -0.06
    POSITIVE LOGITS
     targeting
    0.14
     target
    0.10
    target
    0.10
    Target
    0.09
     Target
    0.09
    _Target
    0.08
    -target
    0.08
    .Target
    0.08
    TARGET
    0.08
    .target
    0.08
    Activations Density 0.010%

    No Known Activations