© 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. 13-LLAMASCOPE-RES-32K
    11. 15279
    Prev
    Next
    INDEX
    Explanations

    programming terms and structures related to condition checks and validations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fore
    -0.16
     full
    -0.16
     mah
    -0.15
    /desktop
    -0.15
     opposite
    -0.15
    ert
    -0.15
     Mah
    -0.15
    andon
    -0.14
    quests
    -0.14
    alf
    -0.14
    POSITIVE LOGITS
     Pieces
    0.17
    ÑĸÑħ
    0.16
    ometr
    0.16
    stadt
    0.15
    ãĥªãĤ«
    0.15
    stm
    0.15
    ucid
    0.14
     Piece
    0.14
    ÃĹ↵↵
    0.14
     illegal
    0.14
    Activations Density 0.215%

    No Known Activations