© 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. 9-LLAMASCOPE-RES-32K
    11. 26819
    Prev
    Next
    INDEX
    Explanations

    phrases that express claims, assertions, or attributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rema
    -0.15
    IFO
    -0.15
     Asi
    -0.15
    ä½į
    -0.15
     bankrupt
    -0.14
     Ara
    -0.14
    MOTE
    -0.14
    lev
    -0.14
    LEV
    -0.14
    inea
    -0.14
    POSITIVE LOGITS
    oho
    0.16
    اع
    0.16
    eker
    0.15
     Wolff
    0.15
     Tic
    0.15
    umi
    0.15
     precious
    0.15
    è¨ĵ
    0.14
     Albania
    0.14
     Eig
    0.14
    Activations Density 0.217%

    No Known Activations