© 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. 22943
    Prev
    Next
    INDEX
    Explanations

    expressions related to pathways and journeys, particularly those involving moving forward or future expectations

    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
    ltk
    -0.20
    adium
    -0.16
    shr
    -0.16
    ÑĪа
    -0.15
    lint
    -0.15
     DIRECT
    -0.15
    sons
    -0.15
     Timing
    -0.14
    loff
    -0.14
     Rating
    -0.14
    POSITIVE LOGITS
     rabbit
    0.25
     road
    0.22
     aisle
    0.20
     Rabbit
    0.20
     drain
    0.20
    river
    0.19
    rabbit
    0.19
     chute
    0.19
     hill
    0.18
    street
    0.18
    Activations Density 0.023%

    No Known Activations