© 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. 17-LLAMASCOPE-RES-131K
    11. 88278
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word 'these' in various contexts

    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
     itself
    -0.08
    ç¯
    -0.07
    _Abstract
    -0.07
    YD
    -0.07
    outil
    -0.07
    ENCIL
    -0.07
    oram
    -0.07
    orst
    -0.07
    odal
    -0.07
    recated
    -0.07
    POSITIVE LOGITS
    curity
    0.12
    cond
    0.11
     days
    0.10
    quence
    0.10
     beiden
    0.09
     kinds
    0.08
     two
    0.08
    cret
    0.07
     things
    0.07
     few
    0.07
    Activations Density 0.076%

    No Known Activations