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. 10-LLAMASCOPE-RES-32K
    6. 29990
    Prev
    Next
    INDEX
    Explanations

    descriptors indicating popularity and preference 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 @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahat
    -0.18
    emax
    -0.17
    oze
    -0.16
    odos
    -0.15
    uges
    -0.15
    udas
    -0.15
    ltk
    -0.14
    rong
    -0.14
    iram
    -0.14
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.14
    POSITIVE LOGITS
    wi
    0.20
    apt
    0.16
    imo
    0.15
    IMO
    0.15
    v
    0.14
    rier
    0.14
    uv
    0.14
    bler
    0.14
    olen
    0.14
    ãİ¡
    0.14
    Activations Density 0.141%

    No Known Activations