INDEX

Explanations

phrases related to environmental or situational conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

thing

-0.19

ache

-0.19

acman

-0.17

one

-0.17

esk

-0.16

ree

-0.15

yst

-0.15

iped

-0.15

coming

-0.15

ao

-0.14

POSITIVE LOGITS

nement

0.18

 circumstances

0.18

0.16

 conditions

0.16

yonel

0.16

ality

0.16

ÙĪØªÛĮ

0.15

RYPTO

0.15

rchive

0.15

Activations Density 0.041%

phrases related to environmental or situational conditions

No Comments

No Known Activations