© 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. 21-LLAMASCOPE-RES-32K
    6. 8780
    Prev
    Next
    INDEX
    Explanations

    the word "true" 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 @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lahoma
    -0.16
    trap
    -0.16
    shed
    -0.16
    shire
    -0.15
    onse
    -0.15
    sburg
    -0.15
    ropolis
    -0.15
    trib
    -0.14
    tron
    -0.14
    land
    -0.13
    POSITIVE LOGITS
    /false
    0.26
    caller
    0.24
    -blue
    0.24
    st
    0.23
    -life
    0.19
    izz
    0.19
    820
    0.17
    sted
    0.17
    -bel
    0.17
    _false
    0.17
    Activations Density 0.024%

    No Known Activations