© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 25528
    Prev
    Next
    INDEX
    Explanations

    concepts related to classification and categorization in various contexts

    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
    ys
    -0.15
    ilar
    -0.15
    zz
    -0.15
    urg
    -0.15
    elf
    -0.14
    248
    -0.14
    &E
    -0.14
    lit
    -0.14
    idis
    -0.14
    anders
    -0.14
    POSITIVE LOGITS
    -like
    0.44
    -style
    0.32
    like
    0.30
    -esque
    0.29
    -type
    0.27
    LIKE
    0.23
    ishly
    0.22
    _like
    0.21
     style
    0.21
    -Type
    0.19
    Activations Density 0.496%

    No Known Activations