© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 19178
    Prev
    Next
    INDEX
    Explanations

    reflections on personal relationships and memories

    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
    /INFO
    -0.15
    è¬
    -0.14
    arti
    -0.13
    izont
    -0.13
    æľĭ
    -0.13
    AlmostEqual
    -0.12
    .presentation
    -0.12
     Restr
    -0.12
    ihilation
    -0.12
    918
    -0.12
    POSITIVE LOGITS
     memory
    0.75
     memories
    0.69
     remember
    0.66
     Memory
    0.64
     remembers
    0.63
    memory
    0.60
    -memory
    0.60
     remembered
    0.59
     remembering
    0.59
     recall
    0.59
    Activations Density 0.669%

    No Known Activations