© 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. 31-LLAMASCOPE-RES-32K
    11. 6001
    Prev
    Next
    INDEX
    Explanations

    negative descriptors and terms related to criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    is
    -0.51
    ia
    -0.40
    d
    -0.32
    ÙĬ
    -0.31
    us
    -0.30
    i
    -0.29
    t
    -0.28
    Ø©
    -0.28
    al
    -0.28
    e
    -0.27
    POSITIVE LOGITS
    ror
    0.17
    othy
    0.17
    thern
    0.16
    bid
    0.15
    respond
    0.15
    theast
    0.15
    phan
    0.14
    بÛĮÙĨ
    0.14
    иÑĪ
    0.14
    rr
    0.13
    Activations Density 0.035%

    No Known Activations