INDEX

Explanations

the presence of the word "on" 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 @ 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

orro

-0.17

yy

-0.15

 Bundy

-0.15

inema

-0.15

YYY

-0.15

min

-0.14

Ted

-0.14

adients

-0.13

orum

-0.13

oor

-0.13

POSITIVE LOGITS

íĥĢ

0.18

æµ¦

0.17

rung

0.16

.Persistent

0.16

 numberWith

0.15

çĽ®

0.15

_safe

0.14

_Tis

0.14

DAQ

0.14

áºŃn

0.14

Activations Density 0.004%

the presence of the word "on" in various contexts

No Comments

No Known Activations