© 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. 5-LLAMASCOPE-RES-131K
    6. 126143
    Prev
    Next
    INDEX
    Explanations

    mentions of care and compassion towards others

    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
    swire
    -0.10
     ÐĵÐŀ
    -0.07
    ngo
    -0.07
    .dx
    -0.07
    iao
    -0.07
    orpion
    -0.07
     Wol
    -0.07
    Fizz
    -0.07
    REA
    -0.07
    ogui
    -0.06
    POSITIVE LOGITS
    ål
    0.06
    fully
    0.06
    ARI
    0.06
     Kai
    0.06
    udge
    0.06
     Wonder
    0.06
     Grund
    0.06
    UDGE
    0.05
     enough
    0.05
    ë
    0.05
    Activations Density 0.003%

    No Known Activations