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. 21-LLAMASCOPE-RES-32K
    6. 9217
    Prev
    Next
    INDEX
    Explanations

    relevant identifiers and key terms related to systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alt
    -0.15
    ãģªãĤĵãģ¦
    -0.14
    ãĢĤãģĬ
    -0.14
    ãĢĤãģĤ
    -0.14
    .CodeAnalysis
    -0.14
    vestment
    -0.13
    ains
    -0.13
    amp
    -0.13
    /portfolio
    -0.13
    ç½
    -0.13
    POSITIVE LOGITS
    _DECL
    0.17
    urple
    0.15
    ieux
    0.15
    ühl
    0.14
    habi
    0.14
    omo
    0.13
    .jd
    0.13
    noinspection
    0.13
    zsche
    0.13
    ücken
    0.13
    Activations Density 0.012%

    No Known Activations