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. 4-LLAMASCOPE-RES-32K
    6. 2420
    Prev
    Next
    INDEX
    Explanations

    themes involving connection and identity

    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
    arat
    -0.16
    jeme
    -0.16
    oft
    -0.15
    orp
    -0.15
    ukkan
    -0.15
     misd
    -0.15
     vir
    -0.14
    edom
    -0.14
    ÑĦÑĦ
    -0.14
    achinery
    -0.14
    POSITIVE LOGITS
    IAS
    0.18
     etc
    0.17
    ิà¸ŀ
    0.14
    etc
    0.14
    ients
    0.14
     Riley
    0.14
    dda
    0.14
     windowHeight
    0.13
    idia
    0.13
    润
    0.13
    Activations Density 0.140%

    No Known Activations