© 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. 29-LLAMASCOPE-RES-32K
    11. 17108
    Prev
    Next
    INDEX
    Explanations

    method calls and string manipulations in programming code

    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
     writ
    -0.17
    ()['
    -0.14
    ovÄĽ
    -0.14
    ().__
    -0.14
     Minority
    -0.13
     Amar
    -0.13
    .strftime
    -0.13
    inp
    -0.13
    bral
    -0.13
    ias
    -0.13
    POSITIVE LOGITS
    .split
    0.31
    split
    0.28
     split
    0.26
     Trim
    0.26
    .trim
    0.26
     trim
    0.26
    Trim
    0.25
    .replace
    0.25
     Split
    0.25
    -split
    0.24
    Activations Density 0.127%

    No Known Activations