© 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. 31-LLAMASCOPE-RES-32K
    11. 5635
    Prev
    Next
    INDEX
    Explanations

    words related to abortion, highlighting varying perspectives in the debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caldwell
    -0.18
    imler
    -0.17
    ÄįÃŃ
    -0.17
    essler
    -0.15
    eners
    -0.15
    ipa
    -0.15
    chin
    -0.15
    chg
    -0.15
    arios
    -0.15
    εÏģι
    -0.14
    POSITIVE LOGITS
    andon
    0.34
    hor
    0.30
    usive
    0.29
    andoned
    0.29
    use
    0.28
    stinence
    0.27
    orted
    0.26
    ortion
    0.26
    uses
    0.26
    normal
    0.25
    Activations Density 0.013%

    No Known Activations