© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 19749
    Prev
    Next
    INDEX
    Explanations

    calls to action or prompts related to viewing and checking content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urement
    -0.14
    ýt
    -0.14
    .portal
    -0.14
    uded
    -0.14
    andid
    -0.14
    -too
    -0.14
    ymous
    -0.13
    iously
    -0.13
    idal
    -0.13
    /from
    -0.13
    POSITIVE LOGITS
     Now
    0.28
    Now
    0.24
     Here
    0.20
    _now
    0.20
     now
    0.20
     Us
    0.20
    /Edit
    0.18
    ed
    0.18
    endon
    0.18
     اÙĦØ¢ÙĨ
    0.17
    Activations Density 0.158%

    No Known Activations