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. 6-LLAMASCOPE-RES-32K
    6. 28299
    Prev
    Next
    INDEX
    Explanations

    citations and references in academic or formal texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    engo
    -0.18
    ugo
    -0.18
    eward
    -0.17
    ISC
    -0.16
    inne
    -0.15
     Ear
    -0.14
    inand
    -0.14
    elling
    -0.14
    busters
    -0.14
    utter
    -0.14
    POSITIVE LOGITS
    AREST
    0.17
    é±
    0.15
    erate
    0.15
    ?url
    0.14
    ÙĬÙĩ
    0.14
    erah
    0.14
    anka
    0.14
    sexual
    0.14
     vie
    0.14
    dba
    0.13
    Activations Density 0.043%

    No Known Activations