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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 20712
    Prev
    Next
    INDEX
    Explanations

    directions and navigational details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     backwards
    -0.16
     Else
    -0.15
    otu
    -0.14
     departure
    -0.14
    kart
    -0.14
    Else
    -0.14
    elp
    -0.14
    oti
    -0.14
    enaire
    -0.13
     Drag
    -0.13
    POSITIVE LOGITS
     reached
    0.32
     reach
    0.31
     reaching
    0.29
     reaches
    0.29
     Reach
    0.28
     Reached
    0.28
    Reach
    0.27
    reach
    0.26
    Reached
    0.25
     erre
    0.23
    Activations Density 0.082%

    No Known Activations