INDEX

Explanations

parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ungi

-0.18

viso

-0.15

itters

-0.14

notated

-0.14

.selenium

-0.14

vincia

-0.14

resse

-0.13

 ÏĮÎ¼ÏīÏĤ

-0.13

umn

-0.13

 )↵↵↵↵↵↵↵↵

-0.13

POSITIVE LOGITS

oret

0.19

 vain

0.15

MS

0.15

sans

0.14

 accent

0.14

odor

0.13

 Rena

0.13

Saf

0.13

aud

0.13

 near

0.13

Activations Density 0.100%

parentheses

No Comments

No Known Activations