© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 1435
    Prev
    Next
    INDEX
    Explanations

    direct quotes or speech in the text

    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
    á»Ŀ
    -0.15
    Ģ
    -0.15
    ="",
    -0.14
    IONS
    -0.14
    bow
    -0.14
    езда
    -0.13
    embro
    -0.13
    aver
    -0.13
     etc
    -0.13
    IntPtr
    -0.13
    POSITIVE LOGITS
    s
    0.20
    yr
    0.15
    hower
    0.14
    sav
    0.14
    arat
    0.14
    yll
    0.14
    ":[{↵
    0.14
    oord
    0.14
    bsite
    0.13
    KF
    0.13
    Activations Density 0.077%

    No Known Activations