© 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. 25-LLAMASCOPE-RES-32K
    6. 17703
    Prev
    Next
    INDEX
    Explanations

    terms related to familial relationships and lineage

    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
    å§Ĭ
    -0.18
     Mom
    -0.17
     Gest
    -0.17
     mom
    -0.17
    ertest
    -0.17
    å§IJ
    -0.16
     mommy
    -0.16
    å¦Ī
    -0.15
    ameda
    -0.15
     mãe
    -0.15
    POSITIVE LOGITS
     grand
    0.68
     Grand
    0.65
    grand
    0.62
    Grand
    0.60
     gran
    0.59
    -grand
    0.58
     grands
    0.56
     grandchildren
    0.55
     Gran
    0.50
     grandson
    0.50
    Activations Density 0.056%

    No Known Activations