© 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. 8-LLAMASCOPE-RES-32K
    11. 30581
    Prev
    Next
    INDEX
    Explanations

    phrases related to effort and persistence in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewood
    -0.15
     Harmon
    -0.15
     swallow
    -0.15
    otti
    -0.14
    rick
    -0.14
    aming
    -0.14
    ullen
    -0.14
    pth
    -0.14
    asure
    -0.14
    ull
    -0.14
    POSITIVE LOGITS
     hard
    0.17
     pack
    0.16
     till
    0.15
    hiba
    0.15
     Rolling
    0.15
    owitz
    0.14
    anos
    0.14
     contested
    0.14
    lip
    0.14
     intensity
    0.14
    Activations Density 0.032%

    No Known Activations