© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119128
    Prev
    Next
    INDEX
    Explanations

    references to human suffering and disaster response

    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
    ¤íĶĦ
    -0.06
    azio
    -0.06
    bra
    -0.06
    ureau
    -0.06
    yre
    -0.06
    ponge
    -0.06
    ATAL
    -0.06
     spy
    -0.06
    á»ĭch
    -0.06
    å®ļ
    -0.06
    POSITIVE LOGITS
    .volley
    0.07
    _Interface
    0.07
     improvis
    0.07
    hani
    0.07
    uka
    0.07
    Priority
    0.07
     Relief
    0.07
     hôm
    0.07
     íķĺ루
    0.06
     daily
    0.06
    Activations Density 0.003%

    No Known Activations