© 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. 25-LLAMASCOPE-RES-32K
    11. 11003
    Prev
    Next
    INDEX
    Explanations

    themes associated with challenge and resilience during difficult times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.18
    žel
    -0.15
    autos
    -0.15
    beiter
    -0.14
    oron
    -0.14
    ame
    -0.14
    oya
    -0.14
    345
    -0.14
    ']!='
    -0.14
    ève
    -0.14
    POSITIVE LOGITS
     times
    0.48
     difficult
    0.43
     tough
    0.41
    times
    0.37
     challenging
    0.34
     Times
    0.33
     toughest
    0.32
     TIMES
    0.32
     Tough
    0.32
     uncertain
    0.30
    Activations Density 0.221%

    No Known Activations