© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 21855
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating levels of difficulty or ease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esson
    -0.20
    olson
    -0.17
    èĪĹ
    -0.16
    elo
    -0.15
     PROCUREMENT
    -0.15
     DISCLAIM
    -0.15
    ouz
    -0.15
    ĩ
    -0.15
    zb
    -0.15
    onga
    -0.15
    POSITIVE LOGITS
     easy
    0.36
    easy
    0.31
     difficult
    0.30
     easier
    0.29
     easiest
    0.26
     impossible
    0.25
    Easy
    0.25
    .easy
    0.25
     Easy
    0.25
     harder
    0.24
    Activations Density 0.067%

    No Known Activations