INDEX

Explanations

phrases indicating action, participation, or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

iel

-0.15

ner

-0.14

https

-0.14

 Ð²ÐµÐºÐ°

-0.14

 https

-0.14

utch

-0.14

uba

-0.13

	goto

-0.13

 concerns

-0.13

POSITIVE LOGITS

 hopefully

0.17

sterol

0.16

ophe

0.15

TextStyle

0.14

.gdx

0.14

sembly

0.14

thew

0.14

leÅŁik

0.14

reesome

0.14

hopefully

0.14

Activations Density 0.040%

phrases indicating action, participation, or states of being

No Comments

No Known Activations