© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 20264
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Bol" and related variations

    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
    rxjs
    -0.15
    renc
    -0.15
    yor
    -0.15
    elow
    -0.15
    lite
    -0.14
     Hib
    -0.14
    ertype
    -0.14
    yx
    -0.14
    reveal
    -0.14
    äll
    -0.14
    POSITIVE LOGITS
    hevik
    0.21
    ivia
    0.21
    ivar
    0.20
    ero
    0.19
    hrad
    0.18
    aji
    0.17
    outu
    0.17
    zano
    0.17
    éro
    0.16
    stered
    0.16
    Activations Density 0.012%

    No Known Activations