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. 11-LLAMASCOPE-RES-32K
    6. 29960
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to conditional statements and block structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erap
    -0.17
    опол
    -0.15
    nev
    -0.15
    forman
    -0.15
    ritte
    -0.14
    iland
    -0.14
     ä½IJ
    -0.14
    avana
    -0.14
    ovenant
    -0.14
    ties
    -0.13
    POSITIVE LOGITS
    _Filter
    0.14
     Vent
    0.14
    íĹĮ
    0.13
    847
    0.13
    inq
    0.13
    hread
    0.13
     Tome
    0.13
     Mayo
    0.13
    MAS
    0.13
     Cors
    0.13
    Activations Density 0.078%

    No Known Activations