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. 16-LLAMASCOPE-RES-32K
    6. 8420
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specificity and quantification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cean
    -0.15
    reas
    -0.14
    amac
    -0.14
    ENTA
    -0.13
    bow
    -0.13
     æ¥
    -0.13
    ยาà¸Ļ
    -0.13
    rames
    -0.13
    .protobuf
    -0.13
    zas
    -0.12
    POSITIVE LOGITS
    addtogroup
    0.15
    _CPP
    0.13
    ÅĻád
    0.13
     prelim
    0.13
    uchen
    0.13
    /background
    0.13
    romise
    0.13
     Persons
    0.12
    ìĿ´íĬ¸
    0.12
    omen
    0.12
    Activations Density 0.071%

    No Known Activations