INDEX

Explanations

phrases indicating negation or absence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

roc

-0.18

seed

-0.16

ãĤ¥

-0.16

rock

-0.15

THREAD

-0.15

ÃľRK

-0.15

strpos

-0.15

nt

-0.14

lik

-0.14

sWith

-0.14

POSITIVE LOGITS

/all

0.19

of

0.18

emachine

0.16

erg

0.16

anners

0.15

.BackgroundImageLayout

0.15

THING

0.15

theless

0.14

ĵ¨

0.14

lected

0.14

Activations Density 0.014%

phrases indicating negation or absence of something

No Comments

No Known Activations