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. 5548
    Prev
    Next
    INDEX
    Explanations

    phrases related to wildlife movement and habitat

    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
    uien
    -0.16
    udd
    -0.15
    ehr
    -0.14
     onAnimation
    -0.14
    .skin
    -0.14
     Smoking
    -0.14
    hausen
    -0.14
    oleon
    -0.13
    olum
    -0.13
     Nich
    -0.13
    POSITIVE LOGITS
     Spread
    0.25
     spread
    0.25
    spread
    0.24
     extent
    0.23
    Spread
    0.22
    extent
    0.21
    æī©
    0.19
     coverage
    0.19
     spreading
    0.19
     spreads
    0.19
    Activations Density 0.146%

    No Known Activations