INDEX

Explanations

instances of the word "to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ynos

-0.16

enga

-0.16

angan

-0.16

abe

-0.14

ulfilled

-0.14

 Prairie

-0.14

 æŃ

-0.13

ãģķãĤĵ

-0.13

anian

-0.13

sci

-0.13

POSITIVE LOGITS

vla

0.16

0.15

ocker

0.15

Fullscreen

0.15

 Horton

0.15

ifu

0.14

TestClass

0.14

baugh

0.14

tea

0.14

 YaÅŁ

0.14

Activations Density 0.041%

instances of the word "to."

No Comments

No Known Activations