INDEX

Explanations

phrases that express existence or presence in a conversational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Anything

-0.14

assis

-0.14

 whatsoever

-0.14

avra

-0.14

skÃ¡

-0.14

.AutoSizeMode

-0.14

urs

-0.14

zelf

-0.14

arendra

-0.13

emaakt

-0.13

POSITIVE LOGITS

 value

0.20

 bound

0.18

 parts

0.18

 worse

0.18

 reasons

0.18

 truth

0.17

 nothing

0.17

 comfort

0.17

 something

0.16

 times

0.16

Activations Density 0.075%

phrases that express existence or presence in a conversational context

No Comments

No Known Activations

phrases that express existence or presence in a conversational context

No Comments

No Known Activations