Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 27773
    Prev
    Next
    INDEX
    Explanations

    variations of the term "IO" and its context related to technology or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mando
    -0.16
    raham
    -0.15
    lose
    -0.15
     Chance
    -0.15
    plied
    -0.15
    shal
    -0.15
    aul
    -0.14
     ziy
    -0.14
    wu
    -0.14
    burgh
    -0.14
    POSITIVE LOGITS
    /ioutil
    0.23
    annis
    0.22
    ivity
    0.17
    .reactivex
    0.16
    .EOF
    0.16
    osphere
    0.15
    iom
    0.15
    ios
    0.15
    Äįan
    0.15
    sep
    0.14
    Activations Density 0.022%

    No Known Activations