© 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. 2-LLAMASCOPE-RES-32K
    6. 5626
    Prev
    Next
    INDEX
    Explanations

    the word "prior" indicating the importance of previous actions or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ECH
    -0.15
    inh
    -0.15
    codec
    -0.14
    æĺł
    -0.14
    uli
    -0.14
    aille
    -0.14
    294
    -0.13
    æŀļ
    -0.13
    inspace
    -0.13
    wy
    -0.13
    POSITIVE LOGITS
    fore
    0.15
    ventus
    0.15
    eco
    0.15
    ayd
    0.15
    æ±½
    0.15
    aby
    0.14
    ents
    0.14
    eing
    0.14
    blas
    0.14
    ÏħÏĦÏĮ
    0.14
    Activations Density 0.007%

    No Known Activations