© 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. 19-LLAMASCOPE-RES-32K
    6. 6201
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to observation and commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isle
    -0.19
    >NN
    -0.15
    ened
    -0.15
    spiel
    -0.15
    -legged
    -0.15
    .AutoScaleMode
    -0.14
    ouz
    -0.14
    ò
    -0.14
    worth
    -0.14
    ahun
    -0.14
    POSITIVE LOGITS
    å¯Ł
    0.22
    vation
    0.20
    /me
    0.19
    ably
    0.19
    à¸ģารà¸ĵ
    0.19
    (obs
    0.18
    ances
    0.18
     observation
    0.18
    /list
    0.17
    297
    0.17
    Activations Density 0.027%

    No Known Activations