INDEX

Explanations

phrases surrounding objectives or goals within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

sel

-0.16

culus

-0.16

urm

-0.15

ogui

-0.14

iki

-0.14

æį

-0.14

oki

-0.14

ghi

-0.13

ulus

-0.13

 Pers

-0.13

POSITIVE LOGITS

aim

0.23

 goal

0.17

utut

0.16

lobe

0.16

Goal

0.16

 aims

0.16

olem

0.16

ingham

0.15

aim

0.15

UCCEEDED

0.15

Activations Density 0.030%

phrases surrounding objectives or goals within the text

No Comments

No Known Activations