© 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. 78833
    Prev
    Next
    INDEX
    Explanations

    discount percentages and promotional offers

    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
    rew
    -0.08
    iams
    -0.07
    گار
    -0.07
     erotische
    -0.07
     kvin
    -0.07
    tual
    -0.07
    á»·
    -0.07
    urse
    -0.07
    metics
    -0.07
     payloads
    -0.07
    POSITIVE LOGITS
    +
    0.07
    iy
    0.06
     toward
    0.06
    ilere
    0.06
    erno
    0.06
    ì§ľ
    0.06
    ile
    0.06
    %
    0.06
    âħ
    0.06
    ead
    0.06
    Activations Density 0.006%

    No Known Activations