© 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. 31-LLAMASCOPE-RES-32K
    6. 6461
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or themes related to the essence of existence and mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Classe
    -0.14
    ÙĪØ·
    -0.14
    ottes
    -0.13
    reating
    -0.13
    AndGet
    -0.13
    .setPrototypeOf
    -0.13
     popularity
    -0.13
    vyk
    -0.12
     batch
    -0.12
     nationally
    -0.12
    POSITIVE LOGITS
     Other
    0.23
     Absolute
    0.21
     Thing
    0.21
     Universe
    0.20
     Unknown
    0.20
     Cosmos
    0.20
     tot
    0.20
     Being
    0.19
     here
    0.19
     Divine
    0.19
    Activations Density 0.330%

    No Known Activations