© 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. 11-LLAMASCOPE-RES-32K
    11. 20640
    Prev
    Next
    INDEX
    Explanations

    phrases related to helpfulness or practical advice

    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
    /group
    -0.16
    .isNullOrEmpty
    -0.16
    aphore
    -0.15
    ilet
    -0.15
    eday
    -0.15
    /IP
    -0.15
    abolic
    -0.14
    edb
    -0.14
     noqa
    -0.13
    actories
    -0.13
    POSITIVE LOGITS
    fully
    0.22
    /help
    0.22
     ÃŃch
    0.21
    aid
    0.16
    /resource
    0.16
    -bodied
    0.16
     information
    0.15
    fulness
    0.15
    /use
    0.14
     coma
    0.14
    Activations Density 0.039%

    No Known Activations