© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 6-LLAMASCOPE-RES-32K
    11. 7559
    Prev
    Next
    INDEX
    Explanations

    error messages related to file inclusion and compilation issues in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fry
    -0.18
    ighted
    -0.15
     boo
    -0.15
     activity
    -0.15
    eto
    -0.14
    Serialized
    -0.14
    ght
    -0.14
    yro
    -0.14
    enti
    -0.14
     ep
    -0.13
    POSITIVE LOGITS
     Fav
    0.20
    @brief
    0.16
    orget
    0.15
    gard
    0.15
     nues
    0.15
     bä
    0.15
    quarters
    0.15
     suất
    0.15
    okud
    0.15
    ük
    0.15
    Activations Density 0.011%

    No Known Activations