INDEX

Explanations

titles of television shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

jab

-0.15

.djang

-0.14

cript

-0.14

kÄ±r

-0.14

utex

-0.14

Ð»Ð¾Ð²Ð°

-0.14

elder

-0.14

genre

-0.13

wan

-0.13

ickness

-0.13

POSITIVE LOGITS

 series

0.20

 spin

0.19

 episodes

0.17

 episode

0.17

 season

0.17

 ãĢľ

0.16

 Incorporated

0.16

 network

0.15

 ìĭľì¦Į

0.15

series

0.15

Activations Density 0.133%

titles of television shows

No Comments

No Known Activations