© 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. 10-LLAMASCOPE-RES-32K
    11. 23132
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or denial of responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruba
    -0.17
    جر
    -0.17
    oklyn
    -0.16
    uzey
    -0.15
    íĥģ
    -0.14
    ë°į
    -0.14
    .Apis
    -0.14
    reopen
    -0.14
    utral
    -0.14
    arel
    -0.14
    POSITIVE LOGITS
     still
    0.18
    obs
    0.17
     mon
    0.16
    acho
    0.14
     fault
    0.14
    ora
    0.14
    era
    0.14
    alt
    0.14
    amine
    0.14
     ainda
    0.14
    Activations Density 0.115%

    No Known Activations