INDEX

Explanations

instances of conditional language indicating alternatives or comparisons

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

trys

-0.15

lobber

-0.15

aginator

-0.14

Gap

-0.14

 subur

-0.14

ant

-0.13

usc

-0.13

iar

-0.13

UBL

-0.13

ugs

-0.13

POSITIVE LOGITS

elow

0.15

itzer

0.15

0.14

ÑħÐ¾Ð´

0.14

ally

0.13

INDER

0.13

.newBuilder

0.13

 Yard

0.13

0.12

Activations Density 0.068%

instances of conditional language indicating alternatives or comparisons

No Comments

No Known Activations