INDEX

Explanations

connections and relationships presented in 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 @ 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

avez

-0.16

.volley

-0.15

();)

-0.15

å½¹

-0.15

udu

-0.15

osl

-0.14

 svens

-0.14

cascade

-0.14

encers

-0.14

pill

-0.14

POSITIVE LOGITS

eros

0.19

EMA

0.17

utra

0.16

iare

0.16

alth

0.15

rot

0.14

 warm

0.14

vel

0.13

Cha

0.13

Previous

0.13

Activations Density 0.262%

connections and relationships presented in the text

No Comments

No Known Activations