INDEX

Explanations

key details related to watch features and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

idel

-0.19

-0.16

ito

-0.15

ica

-0.15

oup

-0.15

 pand

-0.14

_finalize

-0.14

pf

-0.14

ices

-0.14

POSITIVE LOGITS

orman

0.16

ãĥĶãĥ¼

0.15

/rss

0.15

kara

0.14

 Hers

0.14

 ÑģÐ²ÐµÑĢ

0.14

afone

0.14

æ·¡

0.13

 remin

0.13

oshi

0.13

Activations Density 0.009%

key details related to watch features and specifications

No Comments

No Known Activations