INDEX

Explanations

references to trees and tree-related terminology 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ã¶z

-0.17

chsel

-0.16

unt

-0.15

im

-0.14

å·±

-0.14

leo

-0.14

ocache

-0.14

mp

-0.13

emi

-0.13

POSITIVE LOGITS

 whose

0.28

 nÃło

0.23

who

0.22

whose

0.22

 cÃłng

0.20

 ÏĢÎ¿Ïħ

0.20

 that

0.17

who

0.17

 cannot

0.17

cui

0.16

Activations Density 0.253%

references to trees and tree-related terminology in various contexts

No Comments

No Known Activations