© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 23029
    Prev
    Next
    INDEX
    Explanations

    concepts and ideas that involve innovative or theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alnız
    -0.17
    aces
    -0.16
    ings
    -0.16
    anik
    -0.15
    anke
    -0.15
    adow
    -0.15
    agi
    -0.15
    itan
    -0.15
    ança
    -0.15
    OUR
    -0.15
    POSITIVE LOGITS
    ually
    0.54
    ual
    0.44
    UAL
    0.34
    uality
    0.30
    tual
    0.29
    ively
    0.29
    uali
    0.26
    uale
    0.25
    uele
    0.23
    uales
    0.23
    Activations Density 0.024%

    No Known Activations