© 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. 30-LLAMASCOPE-RES-32K
    11. 22259
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    -0.23
    (n
    -0.21
    (m
    -0.19
    (k
    -0.19
    /b
    -0.19
    (h
    -0.18
    (b
    -0.18
    /m
    -0.17
    (
    -0.17
    (g
    -0.17
    POSITIVE LOGITS
    .Syntax
    0.15
    Argb
    0.15
    igung
    0.14
    ertz
    0.14
    anza
    0.14
    setLayout
    0.14
    .getvalue
    0.14
    SharedPtr
    0.13
    .LayoutParams
    0.13
    obia
    0.13
    Activations Density 0.042%

    No Known Activations