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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16636
    Prev
    Next
    INDEX
    Explanations

    terms related to holistic and alternative wellness practices

    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
    antity
    -0.15
    ाण
    -0.14
    Ļæ±Ł
    -0.14
     vigilant
    -0.13
    PointerException
    -0.13
    .MaxLength
    -0.12
    ceptar
    -0.12
    éré
    -0.12
    él
    -0.12
    etur
    -0.12
    POSITIVE LOGITS
     technique
    0.90
     techniques
    0.85
     Technique
    0.75
     Techniques
    0.70
     method
    0.64
    techn
    0.63
     methods
    0.63
     técn
    0.58
     téc
    0.56
    method
    0.55
    Activations Density 0.401%

    No Known Activations