© 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. 31-LLAMASCOPE-RES-32K
    11. 11087
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters often used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ±n
    -0.14
     Deep
    -0.14
     Div
    -0.14
     Pang
    -0.13
    .EXP
    -0.13
    486
    -0.13
    ÙħØ©
    -0.13
     Dat
    -0.13
    oj
    -0.12
    chner
    -0.12
    POSITIVE LOGITS
     bend
    0.22
    arrow
    0.22
     Bend
    0.21
     dashed
    0.20
    dash
    0.20
    dbl
    0.19
    dl
    0.19
    urr
    0.19
    Rightarrow
    0.19
    -arrow
    0.19
    Activations Density 0.015%

    No Known Activations