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. 27-LLAMASCOPE-RES-32K
    6. 19146
    Prev
    Next
    INDEX
    Explanations

    terms related to user access and permissions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phia
    -0.15
     ÏĢÏģά
    -0.15
    )application
    -0.15
    ãģ¡
    -0.14
     zipcode
    -0.14
    ÑĥлÑĮÑĤа
    -0.14
     Hudson
    -0.14
    _ss
    -0.14
     Dob
    -0.14
     Chatt
    -0.14
    POSITIVE LOGITS
     Office
    0.31
    Office
    0.27
     tenant
    0.27
    .office
    0.26
     tenants
    0.24
    AAD
    0.24
     Azure
    0.24
    Azure
    0.23
     Tenant
    0.23
     Yam
    0.23
    Activations Density 0.044%

    No Known Activations