© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 3521
    Prev
    Next
    INDEX
    Explanations

    phrases indicating experience and involvement in various activities over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     now
    -0.19
    now
    -0.16
    _NOW
    -0.15
    ordes
    -0.15
     getenv
    -0.15
     NOW
    -0.14
     Sheldon
    -0.14
    /animate
    -0.14
    ampus
    -0.14
    -now
    -0.14
    POSITIVE LOGITS
     since
    0.15
    ModelState
    0.15
     mechanically
    0.14
    hrad
    0.14
    ATIONAL
    0.14
    ottes
    0.13
    ards
    0.13
     ká»ĥ
    0.13
    ][]
    0.13
    sip
    0.13
    Activations Density 0.096%

    No Known Activations