© 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. 118395
    Prev
    Next
    INDEX
    Explanations

    positional prepositions and phrases indicating location or relation

    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
    halb
    -0.10
    etheless
    -0.09
    lessly
    -0.09
    ำ
    -0.08
    jure
    -0.07
    ends
    -0.07
    -за
    -0.07
    forth
    -0.07
    elow
    -0.07
    elia
    -0.07
    POSITIVE LOGITS
    ä»Ģ
    0.07
    alette
    0.07
     Pou
    0.06
     VÅ¡ech
    0.06
     Cunning
    0.06
    tring
    0.06
    eniable
    0.06
    @nate
    0.06
    eur
    0.06
    _timezone
    0.06
    Activations Density 0.026%

    No Known Activations