INDEX

Explanations

programming-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Hunter

-0.15

à¥įà¤µà¤µ

-0.14

ising

-0.14

ç¹

-0.14

ulen

-0.14

 Theory

-0.14

 grey

-0.13

irmed

-0.13

ienen

-0.13

chw

-0.13

POSITIVE LOGITS

HasBeenSet

0.18

_UNS

0.18

 Ellison

0.17

.Builder

0.15

Å¾e

0.15

è»

0.15

èŃľ

0.14

aÅĻ

0.14

tek

0.14

elda

0.14

Activations Density 0.043%

programming-related terms and concepts

No Comments

No Known Activations