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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 6011
    Prev
    Next
    INDEX
    Explanations

    references to historical or specific details about hospitals and halfway houses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľºåľº
    -0.16
    imuth
    -0.15
    ertil
    -0.14
    зн
    -0.14
    hta
    -0.14
    ìł¤
    -0.14
    ertz
    -0.13
     Mosque
    -0.13
     avid
    -0.13
     Zug
    -0.13
    POSITIVE LOGITS
     institution
    0.34
     orphan
    0.33
     institutional
    0.31
     institutions
    0.31
     Institution
    0.30
     Institutions
    0.29
    institution
    0.29
     san
    0.28
     care
    0.26
     asylum
    0.25
    Activations Density 0.175%

    No Known Activations