INDEX

Explanations

repeated phrases starting with "for."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ophobic

-0.14

urance

-0.14

bens

-0.14

 abduction

-0.13

utters

-0.13

al

-0.13

 bait

-0.13

nger

-0.13

ongo

-0.13

ÑĳÑĢ

-0.13

POSITIVE LOGITS

fu

0.17

 nhau

0.14

UBLE

0.14

agr

0.14

ourg

0.14

Played

0.14

}elseif

0.14

 Depot

0.13

ayo

0.13

ÑĤÐ°Ð±

0.13

Activations Density 0.070%

repeated phrases starting with "for."

No Comments

No Known Activations