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

    Neuronpedia

    Jacobian LensNEW
    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-32K
    11. 31579
    Prev
    Next
    INDEX
    Explanations

    references to actions or states related to "risk."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öst
    -0.17
    odzi
    -0.16
    cker
    -0.16
    igua
    -0.15
    upert
    -0.15
    pst
    -0.15
    azzi
    -0.15
    coni
    -0.14
     Infinite
    -0.14
    Ñĭва
    -0.14
    POSITIVE LOGITS
    RIPT
    0.17
    ì²ľ
    0.15
    atchewan
    0.15
    vos
    0.15
    aya
    0.15
    vie
    0.15
    APE
    0.15
    orpion
    0.15
    iences
    0.14
    ellaneous
    0.14
    Activations Density 0.052%

    No Known Activations