INDEX

Explanations

conjunctions and phrases that indicate comparisons or contrasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ific

-0.16

jo

-0.16

-0.15

 Relief

-0.14

 ÎµÎ»Î»Î·Î½

-0.14

taire

-0.14

Ã¤t

-0.14

 UNUSED

-0.14

ewe

-0.14

_PATCH

-0.13

POSITIVE LOGITS

ppe

0.16

ICES

0.15

lsen

0.15

posables

0.15

Î¿ÏįÏĤ

0.15

stell

0.14

spender

0.14

 repetition

0.14

 detr

0.14

ismatic

0.14

Activations Density 0.264%

conjunctions and phrases that indicate comparisons or contrasts

No Comments

No Known Activations