© 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. 6-LLAMASCOPE-RES-32K
    11. 8027
    Prev
    Next
    INDEX
    Explanations

    references to persistence and continuity in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overall
    -0.15
    athe
    -0.15
    ound
    -0.15
     upon
    -0.15
    prox
    -0.14
    akan
    -0.14
     Upon
    -0.14
     Anc
    -0.14
    .Compute
    -0.14
     cleared
    -0.13
    POSITIVE LOGITS
     escorte
    0.16
    áºŃn
    0.15
    claimer
    0.14
    ालय
    0.14
    ató
    0.14
     ldb
    0.13
    ÙĨÛĮÙĨ
    0.13
    089
    0.13
    ynchronous
    0.13
    adoo
    0.13
    Activations Density 0.134%

    No Known Activations