INDEX

Explanations

titles and prominent phrases from articles likely related to entertainment and culture

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

ouz

-0.15

emap

-0.15

lices

-0.15

annes

-0.14

unday

-0.14

æ

-0.14

ÙĩÙĩ

-0.14

ertain

-0.14

empor

-0.14

ayers

-0.14

POSITIVE LOGITS

>window

0.14

 orbit

0.14

ijke

0.14

_NT

0.13

ZIP

0.13

Streamer

0.13

abis

0.13

ancell

0.13

·

0.13

abl

0.13

Activations Density 0.023%

titles and prominent phrases from articles likely related to entertainment and culture

No Comments

No Known Activations