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. 10-LLAMASCOPE-RES-32K
    6. 21208
    Prev
    Next
    INDEX
    Explanations

    HTML header and sectioning tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egin
    -0.19
    ppo
    -0.15
    asse
    -0.15
    pp
    -0.14
    punk
    -0.14
    ìĤ¬ë¬´
    -0.14
    fare
    -0.14
    loub
    -0.14
    osi
    -0.14
    SSIP
    -0.14
    POSITIVE LOGITS
     Conc
    0.17
     conc
    0.16
    ibri
    0.15
    aurus
    0.14
    FromDate
    0.14
    588
    0.14
     Vend
    0.14
     Maz
    0.14
    HDR
    0.14
    ittel
    0.14
    Activations Density 0.010%

    No Known Activations