© 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. 22-LLAMASCOPE-RES-131K
    11. 4078
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion or sentiment

    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
    esen
    -0.08
    ledon
    -0.08
    ecast
    -0.08
    rophe
    -0.08
    _TestCase
    -0.08
    GuidId
    -0.08
    Č↵
    -0.07
    å±±å¸Ĥ
    -0.07
    HeaderCode
    -0.07
    ấp
    -0.07
    POSITIVE LOGITS
     someone
    0.07
     bless
    0.06
     Bless
    0.06
    all
    0.06
    ohl
    0.06
    una
    0.06
    202
    0.06
    0.06
    666
    0.05
     Someone
    0.05
    Activations Density 0.020%

    No Known Activations