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. 15-LLAMASCOPE-RES-32K
    6. 2816
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to critical conditions and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amba
    -0.15
    depend
    -0.15
    otti
    -0.15
    TREE
    -0.15
    akk
    -0.15
    TED
    -0.14
    TRL
    -0.14
    piel
    -0.14
     elim
    -0.14
    jid
    -0.14
    POSITIVE LOGITS
     DBNull
    0.15
    962
    0.15
     Hod
    0.15
    γκε
    0.14
    unce
    0.14
    lassen
    0.14
     Waterproof
    0.14
    uji
    0.14
    (iOS
    0.14
     Colum
    0.14
    Activations Density 0.004%

    No Known Activations