© 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. 25-LLAMASCOPE-RES-32K
    11. 19216
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and programming structures related to data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;element
    -0.18
    eriod
    -0.16
     имÑĥ
    -0.16
    üns
    -0.15
    icari
    -0.15
     Angiosper
    -0.15
    inke
    -0.14
    URN
    -0.14
    /goto
    -0.14
    \grid
    -0.14
    POSITIVE LOGITS
     c
    0.30
     d
    0.30
     l
    0.28
     v
    0.28
     p
    0.28
     r
    0.27
     w
    0.25
     t
    0.25
     s
    0.24
     m
    0.24
    Activations Density 0.533%

    No Known Activations