INDEX

Explanations

named individuals and their roles or contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

adlo

-0.15

à¤ľà¤¨

-0.14

antor

-0.14

lette

-0.13

imei

-0.13

 humble

-0.13

dh

-0.13

ugins

-0.13

.step

-0.13

uchs

-0.13

POSITIVE LOGITS

bane

0.15

enou

0.14

 pena

0.14

_legend

0.14

ÑĪÐµÐ²

0.14

essel

0.13

ToOne

0.13

 Trou

0.13

 Hastings

0.13

åĨł

0.13

Activations Density 0.469%

named individuals and their roles or contributions

No Comments

No Known Activations