INDEX

Explanations

sequences of characters in various scripts or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÑĽ

-0.14

ereg

-0.13

 Frid

-0.13

Dar

-0.13

lar

-0.13

å©·

-0.13

aspers

-0.12

arrants

-0.12

.info

-0.12

eres

-0.12

POSITIVE LOGITS

.opensource

0.17

linger

0.15

.scalablytyped

0.14

ebe

0.14

asher

0.14

pora

0.13

foil

0.13

Ð¾ÑĢÐ¾Ð¶

0.13

jeta

0.13

 Alphabet

0.13

Activations Density 0.044%

sequences of characters in various scripts or symbols

No Comments

No Known Activations