INDEX

Explanations

terms related to specific biological classifications or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.19

yd

-0.15

 unit

-0.15

Kan

-0.15

ÑĢÐ¾Ñĩ

-0.14

orsk

-0.14

zel

-0.14

upp

-0.14

rot

-0.14

 only

-0.14

POSITIVE LOGITS

icho

0.16

ephy

0.16

(æľ¨

0.15

 nues

0.15

Ð°ÑĢÑĩ

0.15

ichert

0.14

CUS

0.14

vekili

0.14

á»§i

0.14

icol

0.14

Activations Density 0.002%

terms related to specific biological classifications or features

No Comments

No Known Activations