INDEX

Explanations

expressions of significant intensity or emphasis

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

ding

-0.18

ocu

-0.15

mer

-0.15

erties

-0.14

rq

-0.14

illos

-0.14

 Encounter

-0.14

ãĥ¼ãĤ¯

-0.14

wy

-0.14

amas

-0.13

POSITIVE LOGITS

-ÑĤÐ°ÐºÐ¸

0.22

 literally

0.20

 possibly

0.19

 frankly

0.19

ude

0.19

Ã±os

0.17

 Possibly

0.16

 opposite

0.16

possibly

0.15

often

0.14

Activations Density 0.024%

expressions of significant intensity or emphasis

No Comments

No Known Activations