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. 15-LLAMASCOPE-RES-32K
    6. 25144
    Prev
    Next
    INDEX
    Explanations

    themes of self-acceptance and personal empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opa
    -0.15
     nu
    -0.14
    uty
    -0.14
     ><?
    -0.14
     jer
    -0.14
    endo
    -0.14
     ze
    -0.14
     Glover
    -0.14
    ugen
    -0.14
    adr
    -0.14
    POSITIVE LOGITS
     confidence
    0.24
    -confidence
    0.23
    confidence
    0.23
     Confidence
    0.22
     Self
    0.22
     self
    0.20
     SELF
    0.19
    Self
    0.19
    .self
    0.19
     confident
    0.18
    Activations Density 0.099%

    No Known Activations