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. 5-LLAMASCOPE-RES-32K
    6. 161
    Prev
    Next
    INDEX
    Explanations

    references to formal agreements or legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rition
    -0.19
    inition
    -0.18
    tempts
    -0.17
    itionally
    -0.16
    entication
    -0.16
    ServletRequest
    -0.16
    ctor
    -0.15
    ĵåIJį
    -0.15
    StateException
    -0.15
    imately
    -0.15
    POSITIVE LOGITS
    er
    0.52
    a
    0.46
    i
    0.44
    ÛĮ
    0.42
    o
    0.39
    e
    0.39
    y
    0.34
    en
    0.32
    ÙĬ
    0.31
    ëĬĶ
    0.31
    Activations Density 2.352%

    No Known Activations