INDEX

Explanations

phrases indicating future actions or intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

£

-0.16

rael

-0.15

eree

-0.14

Fa

-0.14

[["

-0.14

Ø§Ø±Ú©

-0.13

ÙĨØ¬

-0.13

erville

-0.13

ateral

-0.13

[System

-0.13

POSITIVE LOGITS

bite

0.15

ylan

0.14

å¾Ĵ

0.14

 ReturnType

0.13

Î½Î±Î½

0.13

 convo

0.13

ingleton

0.13

 Sweat

0.13

unner

0.13

 Activation

0.13

Activations Density 0.054%

phrases indicating future actions or intentions

No Comments

No Known Activations