© 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. 3-LLAMASCOPE-RES-32K
    11. 24503
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "resolution" and their contexts, particularly in relation to political actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éra
    -0.17
    erville
    -0.17
    /*č↵
    -0.16
    erman
    -0.16
    ASET
    -0.16
    elay
    -0.16
    ogui
    -0.15
    ipay
    -0.15
    öst
    -0.15
    iek
    -0.15
    POSITIVE LOGITS
     Corm
    0.15
     Mayer
    0.15
    uter
    0.15
    al
    0.15
    de
    0.14
    vents
    0.14
    cial
    0.14
    ÙĪÙĬت
    0.14
    dehyde
    0.14
    lement
    0.14
    Activations Density 0.011%

    No Known Activations