© 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. 2-LLAMASCOPE-RES-32K
    11. 26069
    Prev
    Next
    INDEX
    Explanations

    instances of the word "what" 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 @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -0.16
    èĹ
    -0.15
    bach
    -0.14
    ingles
    -0.14
    .ToShort
    -0.14
    alus
    -0.14
    ifferential
    -0.14
    irie
    -0.14
    ulares
    -0.14
     differential
    -0.13
    POSITIVE LOGITS
    BindingUtil
    0.17
    oko
    0.16
    bsd
    0.16
    ãĥªãĥ¼ãĤº
    0.16
    apan
    0.15
    êµ°ìļĶ
    0.15
    жи
    0.14
    ëĭĪëĭ¤
    0.14
     Gol
    0.13
    èĥ¶
    0.13
    Activations Density 0.018%

    No Known Activations