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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-LLAMASCOPE-RES-32K
    6. 29441
    Prev
    Next
    INDEX
    Explanations

    terms related to loss or negative impacts across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utsch
    -0.16
    antar
    -0.15
     Collapse
    -0.14
    /lists
    -0.14
    gets
    -0.14
    ½
    -0.14
    league
    -0.13
    iyi
    -0.13
    pants
    -0.13
    èµ·æĿ¥
    -0.13
    POSITIVE LOGITS
     Angeles
    0.23
    -loss
    0.20
    ess
    0.19
    (es
    0.19
     mát
    0.18
    ened
    0.18
     sight
    0.17
    ombat
    0.17
    agram
    0.16
    失
    0.16
    Activations Density 0.042%

    No Known Activations