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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 21695
    Prev
    Next
    INDEX
    Explanations

    the presence of personal pronouns and references to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gonna
    -0.23
     unlikely
    -0.22
     likely
    -0.19
     hopefully
    -0.19
    hopefully
    -0.18
    —are
    -0.17
    likely
    -0.17
    ÑĢÑıд
    -0.16
    unlikely
    -0.16
     Likely
    -0.16
    POSITIVE LOGITS
    udo
    0.17
    cctor
    0.15
    pread
    0.14
     Angiospermae
    0.14
    Ø°
    0.14
    uida
    0.14
    ëĶĶìĭľ
    0.14
     zbyt
    0.14
    Scala
    0.13
    uan
    0.13
    Activations Density 0.228%

    No Known Activations