Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 19082
    Prev
    Next
    INDEX
    Explanations

    names or references to individuals, sources, or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acket
    -0.17
     tslib
    -0.17
    jvu
    -0.17
    ̣
    -0.16
    olib
    -0.15
    ahun
    -0.15
    elsing
    -0.14
    achs
    -0.14
    дам
    -0.14
    .gs
    -0.14
    POSITIVE LOGITS
    harma
    0.16
     Guild
    0.16
    ooter
    0.15
    PBS
    0.14
    erti
    0.14
    apy
    0.14
     
    0.14
     erot
    0.13
    enos
    0.13
    ;
    0.13
    Activations Density 0.000%

    No Known Activations