INDEX

Explanations

occurrences of the word "auf" and its variants in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

atu

-0.16

ÙħØª

-0.15

strand

-0.15

jn

-0.15

 Tubes

-0.14

.SDK

-0.14

culus

-0.14

Ã¶h

-0.14

okus

-0.14

nez

-0.13

POSITIVE LOGITS

itch

0.17

ê°Ĳ

0.15

ape

0.15

ipse

0.15

 æ®

0.14

ture

0.14

ìļ´ëıĻ

0.14

screen

0.14

sume

0.14

oser

0.14

Activations Density 0.008%

occurrences of the word "auf" and its variants in various contexts

No Comments

No Known Activations