INDEX

Explanations

phrases containing conditional statements or hypothetical situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

ëħĢ

-0.14

cala

-0.14

Æ°Æ¡i

-0.14

£

-0.13

ompiler

-0.13

 inputs

-0.13

ARGIN

-0.13

-0.12

 Hlav

-0.12

POSITIVE LOGITS

ddb

0.17

anned

0.15

yer

0.14

ifecycle

0.14

ules

0.14

Ã¼m

0.14

 Plat

0.13

 blat

0.13

naments

0.13

anning

0.13

Activations Density 0.009%

phrases containing conditional statements or hypothetical situations

No Comments

No Known Activations