© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 21655
    Prev
    Next
    INDEX
    Explanations

    positive sentiments related to satisfaction and quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coop
    -0.16
    lasses
    -0.13
     hone
    -0.12
    erk
    -0.12
    adaki
    -0.12
    velle
    -0.12
     Begin
    -0.11
    igin
    -0.11
    riter
    -0.11
    asd
    -0.11
    POSITIVE LOGITS
     result
    1.05
     results
    0.98
     outcome
    0.87
    ç»ĵæŀľ
    0.87
    result
    0.87
     Result
    0.85
    çµIJæŀľ
    0.84
     resultado
    0.82
    -result
    0.82
     resultat
    0.81
    Activations Density 0.667%

    No Known Activations