INDEX

Explanations

phrases indicating the absence of something or negative conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

asje

-0.17

à¸µà¸¢à¸Ķ

-0.16

odka

-0.16

è¬Ŀ

-0.15

steam

-0.15

alte

-0.14

edom

-0.14

wy

-0.14

PropertyChanged

-0.13

POSITIVE LOGITS

 except

0.16

bole

0.15

ALS

0.15

erver

0.15

ym

0.14

Ã¡nt

0.14

/all

0.14

chestra

0.14

 imagination

0.14

RY

0.13

Activations Density 0.077%

phrases indicating the absence of something or negative conditions

No Comments

No Known Activations