INDEX

Explanations

terms related to scientific research and academia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

å¡ļ

-0.17

wire

-0.15

addr

-0.15

skin

-0.14

edia

-0.14

 reven

-0.14

ADDR

-0.14

 respectively

-0.14

-0.13

POSITIVE LOGITS

decor

0.14

andro

0.13

éĢ

0.13

 Aspect

0.13

_LD

0.13

(CC

0.13

ÑĩÐ¸ÑģÐ»

0.13

 Santos

0.13

marshall

0.13

 Blend

0.13

Activations Density 0.724%

terms related to scientific research and academia

No Comments

No Known Activations