INDEX

Explanations

phrases indicating existence or presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

iani

-0.20

thern

-0.17

rophe

-0.14

_cpp

-0.14

ern

-0.13

ett

-0.13

ain

-0.13

akens

-0.13

opher

-0.13

ighter

-0.13

POSITIVE LOGITS

INA

0.18

æ´¥

0.16

ento

0.16

unter

0.15

ertain

0.15

Ð±Ð¾Ð²

0.14

 exist

0.14

alto

0.14

HQ

0.14

unto

0.13

Activations Density 0.051%

phrases indicating existence or presence

No Comments

No Known Activations