INDEX

Explanations

references to individual items or components 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

hausen

-0.17

edo

-0.16

uae

-0.15

erken

-0.15

.SwingConstants

-0.14

achten

-0.14

Yao

-0.14

dÃ¼

-0.14

aises

-0.14

anda

-0.14

POSITIVE LOGITS

 Cust

0.19

ĽĦ

0.16

antz

0.16

AsyncResult

0.14

owl

0.14

 cust

0.13

 Dump

0.13

é§ħå¾ĴæŃ©

0.13

.openapi

0.13

unik

0.13

Activations Density 0.170%

references to individual items or components in various contexts

No Comments

No Known Activations