INDEX

Explanations

adjectives that indicate significance, quality, or intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

etro

-0.18

 conc

-0.16

anan

-0.16

 Ø¯Ø§Ø¯

-0.14

conc

-0.14

Gee

-0.14

 Conc

-0.14

utos

-0.13

egan

-0.13

Ð²ÑĢÐ¾Ð¿

-0.13

POSITIVE LOGITS

áº¿

0.16

å¿ľ

0.15

esen

0.15

 Watt

0.15

 than

0.15

gis

0.14

 THAN

0.14

ocos

0.14

illery

0.14

bbox

0.14

Activations Density 0.082%

adjectives that indicate significance, quality, or intensity

No Comments

No Known Activations