INDEX

Explanations

phrases indicating additional content or related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

acad

-0.15

edom

-0.15

osti

-0.14

ó

-0.14

acht

-0.14

 Beled

-0.14

mpp

-0.14

offs

-0.14

 ä¸ĭ

-0.14

ä¸ĭ

-0.14

POSITIVE LOGITS

illon

0.16

Kap

0.14

ktor

0.14

cheon

0.14

jabi

0.14

ington

0.14

cha

0.14

sik

0.14

ardon

0.14

hou

0.13

Activations Density 0.028%

phrases indicating additional content or related topics

No Comments

No Known Activations