© 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. 4-LLAMASCOPE-RES-32K
    11. 3923
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akan
    -0.15
    atica
    -0.14
    aise
    -0.14
    isk
    -0.14
    52
    -0.14
    dle
    -0.14
    ìķĦìĦľ
    -0.13
    nik
    -0.13
     zor
    -0.13
    847
    -0.13
    POSITIVE LOGITS
    ÅĽcie
    0.16
    Arena
    0.16
    olders
    0.15
    izia
    0.15
    ATUS
    0.15
     ucwords
    0.14
    igator
    0.14
    íģ¼
    0.14
    strup
    0.14
    sword
    0.14
    Activations Density 0.022%

    No Known Activations