Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-LLAMASCOPE-RES-32K
    6. 23630
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to recommendations and suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pey
    -0.17
    ATAB
    -0.17
    sun
    -0.15
    веÑī
    -0.15
    oler
    -0.15
     Underground
    -0.15
    ampler
    -0.15
    uman
    -0.14
    ansa
    -0.14
     adaptor
    -0.14
    POSITIVE LOGITS
    ocos
    0.18
    atest
    0.17
    azo
    0.17
    erez
    0.17
    itals
    0.16
    iros
    0.15
    ascus
    0.15
    yth
    0.15
    osing
    0.15
    izr
    0.15
    Activations Density 0.016%

    No Known Activations