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. 18-LLAMASCOPE-RES-32K
    6. 6166
    Prev
    Next
    INDEX
    Explanations

    names and titles related to organizations and community members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coun
    -0.16
     lawmakers
    -0.16
    ekten
    -0.15
     lawmaker
    -0.14
    amer
    -0.14
    tro
    -0.14
     policymakers
    -0.14
    çīĩ
    -0.13
    º
    -0.13
     Pills
    -0.13
    POSITIVE LOGITS
    endum
    0.15
    _HAS
    0.15
    avern
    0.14
    ospace
    0.14
    chwitz
    0.14
    ï¼ł
    0.14
    elight
    0.14
    resar
    0.13
    ICENSE
    0.13
    undry
    0.13
    Activations Density 0.003%

    No Known Activations