© 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. 2-LLAMASCOPE-RES-32K
    11. 28048
    Prev
    Next
    INDEX
    Explanations

    sentences that express fear or hesitation regarding taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    輪
    -0.15
    è®
    -0.15
    azio
    -0.15
    ials
    -0.14
    .fi
    -0.14
    ÑĥÑĩа
    -0.14
    neau
    -0.13
    ached
    -0.13
     имÑĥ
    -0.13
     immune
    -0.13
    POSITIVE LOGITS
     McMahon
    0.16
    ifter
    0.16
    tro
    0.16
    Tro
    0.15
    اذ
    0.14
    iris
    0.14
    brid
    0.14
    تÙĬÙĨ
    0.14
    ÏĢη
    0.14
    _slope
    0.14
    Activations Density 0.013%

    No Known Activations