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. 25-LLAMASCOPE-RES-32K
    6. 16899
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and positive feedback regarding quality of work or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ặt
    -0.16
    jez
    -0.15
    zi
    -0.15
    @js
    -0.14
    igy
    -0.13
    енка
    -0.13
    COPE
    -0.13
    247
    -0.13
    _utilities
    -0.13
    iran
    -0.13
    POSITIVE LOGITS
     job
    1.52
    job
    1.25
     Job
    1.24
    Job
    1.14
    -job
    1.11
     JOB
    1.10
     jobs
    1.06
    _job
    1.01
    .job
    0.95
    (job
    0.91
    Activations Density 0.143%

    No Known Activations