© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89825
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their relationships to 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
    upe
    -0.08
    (CType
    -0.07
    bcm
    -0.07
    XObject
    -0.07
    turnstile
    -0.07
    ract
    -0.07
    ìħĶ
    -0.07
    utedString
    -0.07
    _Tis
    -0.07
    hsi
    -0.07
    POSITIVE LOGITS
     phrase
    0.07
    ç¹ģ
    0.06
     frase
    0.06
     fa
    0.05
    Phrase
    0.05
     Phrase
    0.05
     numberOfRowsInSection
    0.05
     phrases
    0.05
    angle
    0.05
     Fa
    0.05
    Activations Density 0.020%

    No Known Activations