© 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. 22418
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "get" and its variations along with related themes of achieving or obtaining

    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
    xis
    -0.16
    844
    -0.16
    858
    -0.14
    ocz
    -0.14
    artial
    -0.14
    .BackgroundImageLayout
    -0.13
    uthor
    -0.13
     Lobby
    -0.13
    arella
    -0.13
    fare
    -0.13
    POSITIVE LOGITS
     along
    0.87
    along
    0.77
     Along
    0.75
    Along
    0.71
    沿
    0.47
    -al
    0.45
    _al
    0.41
     alongside
    0.35
     junto
    0.35
     AL
    0.32
    Activations Density 0.127%

    No Known Activations