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. 23-LLAMASCOPE-RES-32K
    6. 11936
    Prev
    Next
    INDEX
    Explanations

    phrases indicating dissatisfaction or critiques of quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SCO
    -0.15
    USA
    -0.14
     gradu
    -0.14
     intimately
    -0.14
    gue
    -0.14
    anga
    -0.14
    ffa
    -0.14
     equally
    -0.13
     correct
    -0.13
    DT
    -0.13
    POSITIVE LOGITS
     struct
    0.17
     quiet
    0.17
    بس
    0.16
     peaceful
    0.16
     litter
    0.16
     unique
    0.16
     UNIQUE
    0.15
     CLEAN
    0.15
     backward
    0.15
    寧
    0.15
    Activations Density 0.010%

    No Known Activations