© 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. 6-LLAMASCOPE-RES-32K
    11. 7987
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax elements related to programming languages, particularly in JavaScript

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oš
    -0.17
    jac
    -0.15
    _reserved
    -0.15
    erea
    -0.14
    ariat
    -0.14
    bian
    -0.14
    LineColor
    -0.14
    ulen
    -0.13
    phalt
    -0.13
    vens
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĥĸ
    0.18
    roi
    0.15
    عر
    0.15
    isters
    0.15
    ASSES
    0.14
    orget
    0.14
    ITLE
    0.14
    getSimpleName
    0.14
    AKER
    0.14
    æ²ĥ
    0.14
    Activations Density 0.130%

    No Known Activations