© 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. 12-LLAMASCOPE-RES-32K
    11. 15160
    Prev
    Next
    INDEX
    Explanations

    the word "while" and its usage in contrasting contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ese
    -0.16
    .UnitTesting
    -0.15
    ÙĨÙĬÙĨ
    -0.15
    lobber
    -0.15
    ا
    -0.14
    eye
    -0.14
    eselect
    -0.14
    Ùĭا
    -0.14
    ant
    -0.14
    æľ¬å½ĵ
    -0.14
    POSITIVE LOGITS
    s
    0.35
    sap
    0.19
    tty
    0.18
    itzer
    0.18
    sheets
    0.18
    sad
    0.17
    azen
    0.17
    bij
    0.16
    sam
    0.16
    sink
    0.16
    Activations Density 0.027%

    No Known Activations