© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123604
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or consequences

    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
    arias
    -0.07
    ëŀij
    -0.07
    zion
    -0.07
    .ds
    -0.06
    串
    -0.06
    plementation
    -0.06
    /sm
    -0.06
    먹
    -0.06
    CTYPE
    -0.06
    ADDE
    -0.06
    POSITIVE LOGITS
     its
    0.18
     Its
    0.13
    Its
    0.11
    åħ¶
    0.11
     their
    0.10
    its
    0.10
     being
    0.09
     fact
    0.08
     sua
    0.07
     they
    0.07
    Activations Density 0.028%

    No Known Activations