INDEX

Explanations

phrases indicating a lack 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

åħ

-0.16

ents

-0.15

åħ¸

-0.15

yang

-0.15

anten

-0.14

enty

-0.14

getInstance

-0.14

tas

-0.14

rias

-0.14

éĢ±

-0.14

POSITIVE LOGITS

ritz

0.16

tul

0.15

poÄįet

0.15

avou

0.14

ÏĥÎ®

0.14

acher

0.14

lesen

0.14

 proper

0.13

 properly

0.13

Activations Density 0.020%

phrases indicating a lack or absence of something

No Comments

No Known Activations