INDEX

Explanations

words conveying actions and states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

borg

-0.15

MouseButton

-0.14

ije

-0.14

lip

-0.14

ica

-0.13

_DICT

-0.13

male

-0.13

aurus

-0.13

xic

-0.13

POSITIVE LOGITS

anj

0.19

anje

0.15

aan

0.14

 pinch

0.14

unan

0.14

wire

0.14

 minus

0.14

aland

0.13

apr

0.13

CCR

0.13

Activations Density 0.009%

words conveying actions and states of being

No Comments

No Known Activations