INDEX

Explanations

phrases related to terms and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

anh

-0.19

olin

-0.16

igh

-0.16

inn

-0.15

_catalog

-0.15

erts

-0.15

currentColor

-0.15

eday

-0.15

IGH

-0.15

cue

-0.15

POSITIVE LOGITS

use

0.23

Use

0.23

 service

0.20

Use

0.20

-use

0.19

_use

0.18

 Service

0.17

petto

0.17

Conditions

0.17

 Conditions

0.16

Activations Density 0.012%

phrases related to terms and conditions

No Comments

No Known Activations