INDEX

Explanations

mentions of specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.17

lund

-0.16

-0.15

ÑĮÐºÐ¾

-0.15

eral

-0.15

ergy

-0.15

bou

-0.15

(nameof

-0.15

 prim

-0.14

sac

-0.14

POSITIVE LOGITS

ulin

0.17

ply

0.16

Î»Ïİ

0.14

ISTA

0.14

 derec

0.14

kus

0.14

à¤®à¤¤

0.14

ï¼Īå¹³æĪĲ

0.14

forest

0.13

zew

0.13

Activations Density 0.033%

mentions of specific years

No Comments

No Known Activations