© 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. 29-LLAMASCOPE-RES-32K
    11. 4571
    Prev
    Next
    INDEX
    Explanations

    phrases indicating smallness or modesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acker
    -0.17
    _UNUSED
    -0.15
    stå
    -0.15
    åľ¨
    -0.15
    InParameter
    -0.14
    ÃĹ↵↵
    -0.14
    zure
    -0.14
    zeit
    -0.14
     sourceMapping
    -0.13
    awaiter
    -0.13
    POSITIVE LOGITS
     manner
    0.48
     nutshell
    0.40
     way
    0.38
     hurry
    0.35
     effort
    0.31
     bid
    0.29
     fashion
    0.27
     attempt
    0.24
     matter
    0.24
     heartbeat
    0.24
    Activations Density 0.130%

    No Known Activations