© 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. 126287
    Prev
    Next
    INDEX
    Explanations

    statements about intent and meaning in communication

    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
    á»ĵi
    -0.07
    LETE
    -0.07
    abbage
    -0.07
    iken
    -0.06
    ropy
    -0.06
    ken
    -0.06
    achten
    -0.06
    ÅŁt
    -0.06
    Ken
    -0.06
    aze
    -0.06
    POSITIVE LOGITS
     meant
    0.11
     offense
    0.10
     offence
    0.10
     intended
    0.08
     disrespect
    0.08
    åĨĴ
    0.08
     mean
    0.08
     offend
    0.07
    ynet
    0.07
     Mean
    0.07
    Activations Density 0.028%

    No Known Activations