Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 12697
    Prev
    Next
    INDEX
    Explanations

    references to sports injuries and player statuses

    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
     Commentary
    -0.15
    ifact
    -0.15
    Postal
    -0.14
    ueil
    -0.14
    erged
    -0.14
    $form
    -0.14
    CKER
    -0.14
    axies
    -0.13
    ÑĥÑī
    -0.13
    formik
    -0.13
    POSITIVE LOGITS
     listed
    0.21
     statuses
    0.21
     status
    0.20
     questionable
    0.19
    status
    0.17
    listed
    0.17
     listings
    0.17
    -status
    0.17
     active
    0.17
     dressed
    0.17
    Activations Density 0.043%

    No Known Activations