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. 7-LLAMASCOPE-RES-32K
    6. 7476
    Prev
    Next
    INDEX
    Explanations

    references to conditions or specifications in a formula or mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĤİ
    -0.15
    .LA
    -0.15
    otec
    -0.15
    vinces
    -0.14
    onen
    -0.14
    EncodingException
    -0.14
    iores
    -0.14
    irit
    -0.14
    ife
    -0.14
    gage
    -0.14
    POSITIVE LOGITS
    utar
    0.14
    endi
    0.14
    'gc
    0.14
    _COMPAT
    0.13
    ousse
    0.13
     overhead
    0.13
    .scalablytyped
    0.13
     Ear
    0.13
     Guerrero
    0.13
    dden
    0.13
    Activations Density 0.030%

    No Known Activations