INDEX

Explanations

words related to transitions or changes in situations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ube

-0.17

stroy

-0.15

-0.14

Enumerator

-0.14

dn

-0.14

rame

-0.14

aleb

-0.14

ikit

-0.14

 ramp

-0.14

lbrace

-0.14

POSITIVE LOGITS

íİ¸

0.18

olley

0.16

ijken

0.15

alink

0.15

arte

0.15

 pars

0.14

ãĢħ

0.14

ØºÙĬØ±

0.13

aran

0.13

bai

0.13

Activations Density 0.277%

words related to transitions or changes in situations

No Comments

No Known Activations