INDEX

Explanations

phrases indicating 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

iem

-0.15

aldi

-0.14

alink

-0.14

 ranks

-0.14

_DELETED

-0.14

.mk

-0.13

maker

-0.13

assa

-0.13

ivet

-0.13

ovky

-0.13

POSITIVE LOGITS

0.16

gte

0.15

geo

0.15

ë¥¸

0.14

andest

0.14

-END

0.14

INAL

0.14

gn

0.14

Activations Density 0.073%

phrases indicating comparisons or contrasts

No Comments

No Known Activations