INDEX

Explanations

terms related to mechanisms and processes 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 @ 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

enance

-0.18

Ø¬Ùħ

-0.16

anca

-0.15

TING

-0.15

ifice

-0.15

unan

-0.15

avl

-0.14

teen

-0.14

gel

-0.14

elman

-0.14

POSITIVE LOGITS

ic

0.24

ically

0.19

isms

0.18

(s

0.16

 Mechan

0.16

rts

0.16

 mechanisms

0.15

æĢ§çļĦ

0.15

hift

0.15

rch

0.15

Activations Density 0.026%

terms related to mechanisms and processes in various contexts

No Comments

No Known Activations