© 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. 14-LLAMASCOPE-RES-32K
    11. 12263
    Prev
    Next
    INDEX
    Explanations

    references to mental health topics and their impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ìī
    -0.15
    нож
    -0.15
    uzzi
    -0.14
    Recovered
    -0.14
    listing
    -0.13
    ););↵
    -0.13
     stacks
    -0.13
    ker
    -0.13
     há»ĵi
    -0.13
     Stack
    -0.13
    POSITIVE LOGITS
    IDES
    0.15
    ساÙĨÛĮ
    0.14
    OrNil
    0.14
    ntag
    0.14
     smooth
    0.14
    NECT
    0.14
     Studies
    0.14
    _WRONG
    0.14
    eras
    0.14
    olland
    0.13
    Activations Density 0.024%

    No Known Activations