INDEX

Explanations

words describing quality, performance, and aesthetics in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÎµÏį

-0.16

atts

-0.15

anga

-0.15

acco

-0.15

uhl

-0.14

Å¡el

-0.14

ughs

-0.14

inja

-0.14

aca

-0.13

/ui

-0.13

POSITIVE LOGITS

 purposes

0.16

.ll

0.16

#elif

0.15

 desired

0.15

 further

0.14

mus

0.14

Ã©ric

0.14

getDisplay

0.13

 omas

0.13

Activations Density 0.350%

words describing quality, performance, and aesthetics in various contexts

No Comments

No Known Activations