© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 19154
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and its variations, particularly in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _FE
    -0.17
    achs
    -0.14
    žel
    -0.14
    ¢åįķ
    -0.14
    ourt
    -0.14
    ãĤ±ãĥ¼ãĤ¹
    -0.14
    ÑĪкÑĥ
    -0.14
    ileo
    -0.14
    et
    -0.13
    fec
    -0.13
    POSITIVE LOGITS
    seg
    0.18
    nah
    0.17
    llu
    0.16
    VERN
    0.16
    iqu
    0.15
     superf
    0.15
    lbl
    0.15
    ATHER
    0.15
    lap
    0.14
    nen
    0.14
    Activations Density 0.007%

    No Known Activations