© 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. 17785
    Prev
    Next
    INDEX
    Explanations

    assessments of narrative structure and coherence in storytelling

    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
     Worksheets
    -0.14
    lig
    -0.14
    azon
    -0.14
    äºĶæľĪ
    -0.14
    à¹ĥà¸ļ
    -0.14
    igne
    -0.13
    anos
    -0.13
    anno
    -0.13
    eyed
    -0.13
     cords
    -0.13
    POSITIVE LOGITS
     length
    0.44
     longer
    0.39
    length
    0.38
     longest
    0.36
    éķ¿åº¦
    0.36
    -length
    0.36
     Length
    0.35
     lenght
    0.34
     LENGTH
    0.33
     shorter
    0.32
    Activations Density 0.192%

    No Known Activations