INDEX

Explanations

references to actions of raising or lifting

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

hot

-0.16

ize

-0.15

hot

-0.15

tem

-0.13

ReadOnly

-0.13

 Compass

-0.13

 tang

-0.13

_compile

-0.13

uple

-0.13

tan

-0.13

POSITIVE LOGITS

ÙĪØ¹

0.18

invisible

0.16

awl

0.15

SSERT

0.15

emoc

0.15

enco

0.15

Ã¢l

0.14

mite

0.14

eah

0.14

juries

0.14

Activations Density 0.009%

references to actions of raising or lifting

No Comments

No Known Activations