© 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. 19576
    Prev
    Next
    INDEX
    Explanations

    specific locations and addresses associated with businesses and services

    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
    ìĬ´
    -0.14
    ì¶ĺ
    -0.14
    ?↵↵↵↵
    -0.14
    Č↵
    -0.14
    овÑĸ
    -0.14
    058
    -0.14
    è¼Ŀ
    -0.14
    <small
    -0.13
     ord
    -0.13
    056
    -0.13
    POSITIVE LOGITS
     Suite
    0.36
     corner
    0.32
     PO
    0.32
     suite
    0.32
    Suite
    0.31
    PO
    0.30
    corner
    0.29
    suite
    0.26
     suites
    0.26
     Corner
    0.25
    Activations Density 0.101%

    No Known Activations