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. 30-LLAMASCOPE-RES-32K
    6. 11146
    Prev
    Next
    INDEX
    Explanations

    references to well-known individuals and institutions, particularly in the context of news and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĢид
    -0.17
    éĢı
    -0.17
    ried
    -0.17
    iker
    -0.16
    abbage
    -0.15
    ¼åIJĪ
    -0.15
    èo
    -0.14
    ÑĢива
    -0.14
    eger
    -0.14
    rement
    -0.14
    POSITIVE LOGITS
     ho
    0.16
    arms
    0.15
    ë³¼
    0.15
    ire
    0.15
     preliminary
    0.14
     ty
    0.14
    raj
    0.14
     Sty
    0.14
    .bold
    0.14
    vest
    0.14
    Activations Density 0.030%

    No Known Activations