© 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. 22855
    Prev
    Next
    INDEX
    Explanations

    references to books and related media

    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
    igm
    -0.18
     booking
    -0.18
    ept
    -0.17
    brook
    -0.16
    _booking
    -0.16
     bookings
    -0.15
    economic
    -0.15
    esModule
    -0.15
    monds
    -0.15
    avel
    -0.15
    POSITIVE LOGITS
    shelf
    0.39
    ç±į
    0.35
    ends
    0.32
    worm
    0.31
    stores
    0.31
    keeping
    0.30
    ellers
    0.28
    eller
    0.28
    azine
    0.28
    lets
    0.28
    Activations Density 0.072%

    No Known Activations