© 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. 4-LLAMASCOPE-RES-32K
    6. 2277
    Prev
    Next
    INDEX
    Explanations

    references to tweets and social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شتÙĩ
    -0.15
    lopen
    -0.14
     priesthood
    -0.13
    wi
    -0.13
    usty
    -0.13
    ì§ģ
    -0.13
     Clipboard
    -0.13
    æľ
    -0.13
     Hoffman
    -0.12
    iaz
    -0.12
    POSITIVE LOGITS
    stakes
    0.15
    entieth
    0.15
     Äiju
    0.14
    inox
    0.14
    ven
    0.14
    etas
    0.14
    _WAKE
    0.14
    rogen
    0.14
    phas
    0.14
    earth
    0.14
    Activations Density 0.018%

    No Known Activations