INDEX

Explanations

numeric identifiers or codes related to organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

idon

-0.17

ymbol

-0.16

zar

-0.16

ncoder

-0.16

opak

-0.16

zac

-0.15

rated

-0.15

koa

-0.15

gard

-0.15

outil

-0.14

POSITIVE LOGITS

 Fram

0.15

.createFrom

0.15

-src

0.15

 frames

0.15

0.14

ined

0.14

 fram

0.14

lup

0.14

INFO

0.14

ÑģÑĤÐ²

0.14

Activations Density 0.029%

numeric identifiers or codes related to organizations or entities

No Comments

No Known Activations