© 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. 17-LLAMASCOPE-RES-32K
    11. 30750
    Prev
    Next
    INDEX
    Explanations

    instances of the word "listen" and its variations, indicating a focus on listening experiences and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    547
    -0.17
    urv
    -0.16
    heat
    -0.16
    lette
    -0.15
     Bloss
    -0.15
    ulent
    -0.15
    MENT
    -0.15
    iled
    -0.15
    ément
    -0.14
    uples
    -0.14
    POSITIVE LOGITS
    /watch
    0.28
    AndServe
    0.23
    /view
    0.19
     ears
    0.19
    tower
    0.16
     closely
    0.16
    ears
    0.15
     carefully
    0.15
    eners
    0.15
    ardo
    0.15
    Activations Density 0.034%

    No Known Activations