Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4468
    Prev
    Next
    INDEX
    Explanations

    negative emotional states or conflicts

    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
    _MAY
    -0.08
    .SDK
    -0.07
    ennen
    -0.07
    haft
    -0.07
    ellungen
    -0.07
    filme
    -0.07
    ntag
    -0.06
    olit
    -0.06
    .MixedReality
    -0.06
    atures
    -0.06
    POSITIVE LOGITS
     pap
    0.07
    jon
    0.06
     Mar
    0.06
     Sob
    0.06
     Ion
    0.06
     Pond
    0.05
    654
    0.05
     unp
    0.05
    jom
    0.05
     pur
    0.05
    Activations Density 0.000%

    No Known Activations