© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 6-LLAMASCOPE-RES-32K
    11. 6686
    Prev
    Next
    INDEX
    Explanations

    instances of the word "demonstrate" and its variations, indicating a focus on showing or proving concepts or skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.17
    fulness
    -0.17
    legg
    -0.16
     dus
    -0.15
     Manning
    -0.14
    .DefaultCellStyle
    -0.14
    se
    -0.14
    ãĢħ
    -0.14
    ãĥ¼ãĥ«
    -0.14
    ful
    -0.14
    POSITIVE LOGITS
    stration
    0.18
    strate
    0.17
    ively
    0.17
    altitude
    0.16
     postcode
    0.16
    419
    0.15
    andi
    0.15
    769
    0.15
    749
    0.15
    ÅĽli
    0.14
    Activations Density 0.024%

    No Known Activations