INDEX

Explanations

variations of the verb "look"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

á»ĭch

-0.17

egal

-0.16

les

-0.16

addin

-0.14

uner

-0.14

vero

-0.14

.until

-0.14

uka

-0.14

cod

-0.14

eca

-0.14

POSITIVE LOGITS

 around

0.21

 upon

0.21

 down

0.21

 away

0.18

sky

0.18

up

0.17

 elsewhere

0.17

dag

0.17

 directly

0.17

 straight

0.16

Activations Density 0.044%

variations of the verb "look"

No Comments

No Known Activations