© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 11647
    Prev
    Next
    INDEX
    Explanations

    instances of articles and their relationships to nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑģоÑĢ
    -0.14
    .scalablytyped
    -0.14
    amage
    -0.14
    pch
    -0.14
    roups
    -0.14
    yna
    -0.13
    PasswordEncoder
    -0.13
    IH
    -0.13
    oso
    -0.13
    icros
    -0.13
    POSITIVE LOGITS
     host
    0.48
     raft
    0.35
     ton
    0.33
     whole
    0.33
    host
    0.32
     string
    0.32
     slew
    0.32
     bev
    0.31
     wealth
    0.30
     be
    0.29
    Activations Density 0.240%

    No Known Activations