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. 22-LLAMASCOPE-RES-32K
    6. 20251
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts related to attributes, features, and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igate
    -0.17
    AML
    -0.15
    .tell
    -0.14
    shan
    -0.14
    158
    -0.13
    agma
    -0.13
    181
    -0.13
    _firestore
    -0.13
    them
    -0.13
    chang
    -0.12
    POSITIVE LOGITS
     we
    0.30
     they
    0.28
     you
    0.21
     he
    0.21
     it
    0.21
     she
    0.19
    soever
    0.19
     exactly
    0.17
     они
    0.17
     à¤īसन
    0.16
    Activations Density 0.078%

    No Known Activations