© 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. 22-LLAMASCOPE-RES-32K
    11. 20269
    Prev
    Next
    INDEX
    Explanations

    code-related elements in a web development context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paz
    -0.18
    .mj
    -0.17
     sil
    -0.16
    rxjs
    -0.14
    .curve
    -0.14
    agher
    -0.14
     Sanct
    -0.14
     Clair
    -0.14
    etro
    -0.14
    combe
    -0.14
    POSITIVE LOGITS
     Pag
    0.20
    .jquery
    0.16
    icho
    0.15
    erner
    0.15
    XYZ
    0.15
    idden
    0.15
    ounder
    0.15
     Purple
    0.15
    717
    0.15
    oure
    0.15
    Activations Density 0.002%

    No Known Activations