INDEX

Explanations

mentions of notable individuals in a context related to performance 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

baz

-0.15

idget

-0.15

 Antworten

-0.15

æĢ§

-0.15

imir

-0.14

obra

-0.14

iÃŁ

-0.14

tiles

-0.14

niÅ¾

-0.13

ä¸²

-0.13

POSITIVE LOGITS

rix

0.14

æ·»

0.14

 redraw

0.14

enberg

0.14

_ASSUME

0.14

stras

0.13

å¿ł

0.13

 quang

0.13

ura

0.13

 tips

0.13

Activations Density 0.226%

mentions of notable individuals in a context related to performance or contributions

No Comments

No Known Activations