INDEX

Explanations

phrases indicating cause and effect relationships

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

 INTERRU

-0.15

(çģ«

-0.14

ãĢĳ,ãĢĲ

-0.14

estation

-0.14

abbo

-0.14

_REQUIRED

-0.14

-0.13

ismet

-0.13

tek

-0.13

lox

-0.13

POSITIVE LOGITS

kit

0.15

umo

0.14

ync

0.14

uma

0.14

 bomb

0.14

 retention

0.14

è³¢

0.14

kit

0.13

 lipid

0.13

 Misc

0.13

Activations Density 0.292%

phrases indicating cause and effect relationships

No Comments

No Known Activations