Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19477
    Prev
    Next
    INDEX
    Explanations

    phrases related to enhancing or changing experiences or environments

    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
    vertime
    -0.14
    uyo
    -0.13
     Antar
    -0.13
    Descending
    -0.12
    ownload
    -0.12
     поÑĩ
    -0.12
     downward
    -0.12
    edir
    -0.12
    tsx
    -0.12
    apis
    -0.11
    POSITIVE LOGITS
     up
    1.47
    -up
    1.14
    up
    1.14
     Up
    1.02
    Up
    0.98
    _up
    0.98
    .up
    0.92
    -Up
    0.90
    	up
    0.82
    (up
    0.80
    Activations Density 1.309%

    No Known Activations