© 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. 30-LLAMASCOPE-RES-32K
    6. 22862
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical data and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adolescents
    -0.23
     Adoles
    -0.23
     Teen
    -0.23
     teenager
    -0.22
     Teens
    -0.22
    teen
    -0.21
     teenagers
    -0.21
    Teen
    -0.21
     adolescence
    -0.21
     teens
    -0.21
    POSITIVE LOGITS
    24
    0.65
    25
    0.61
    26
    0.59
    23
    0.53
    27
    0.48
     twenty
    0.42
    28
    0.41
     Twenty
    0.38
    22
    0.36
    024
    0.35
    Activations Density 0.171%

    No Known Activations