© 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. 23-LLAMASCOPE-RES-32K
    11. 28574
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nullptr
    -0.20
    ,std
    -0.17
    nullptr
    -0.17
    ektiv
    -0.16
    (std
    -0.16
    (nullptr
    -0.16
    std
    -0.15
    [string
    -0.15
    itia
    -0.15
     DCHECK
    -0.15
    POSITIVE LOGITS
     char
    0.40
     struct
    0.36
     void
    0.30
    char
    0.29
    struct
    0.29
     int
    0.25
    	char
    0.25
    (char
    0.23
    void
    0.23
    (struct
    0.23
    Activations Density 0.074%

    No Known Activations