© 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. 26-LLAMASCOPE-RES-32K
    11. 21913
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs, specifically functions and their declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooth
    -0.17
     "
    -0.15
    din
    -0.14
    omy
    -0.14
    ĻĤ
    -0.14
     '
    -0.14
    (()=>
    -0.14
    bum
    -0.14
     cellspacing
    -0.14
    hood
    -0.13
    POSITIVE LOGITS
     (*
    0.20
     Marshal
    0.17
    464
    0.17
    ((*
    0.17
     New
    0.17
     Dial
    0.16
    .(*
    0.16
     Benchmark
    0.16
     ((*
    0.16
     marshal
    0.16
    Activations Density 0.006%

    No Known Activations