© 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. 16-LLAMASCOPE-RES-32K
    6. 22305
    Prev
    Next
    INDEX
    Explanations

    names of deceased individuals along with their professions and relevant dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andin
    -0.17
    ivas
    -0.15
    structor
    -0.15
    aat
    -0.15
    oyer
    -0.14
    lier
    -0.14
    ãĥ¥ãĥ¼
    -0.13
    andr
    -0.13
    pez
    -0.13
    atin
    -0.13
    POSITIVE LOGITS
    avenport
    0.16
    yles
    0.15
     moden
    0.14
    printStats
    0.14
    rippling
    0.14
    okud
    0.14
    dit
    0.13
    matchCondition
    0.13
    uro
    0.13
    adena
    0.13
    Activations Density 0.024%

    No Known Activations