INDEX

Explanations

phrases and references related to guidelines and cultural artifacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

yonel

-0.15

ĶĦ

-0.15

Î¸Î®

-0.15

º

-0.14

oup

-0.14

Ð¾Ð½ÑĮ

-0.14

ekli

-0.14

WL

-0.14

inspace

-0.14

ÐµÐ½Ð½Ñĸ

-0.14

POSITIVE LOGITS

assel

0.16

 Chap

0.16

alie

0.16

 stable

0.16

 partial

0.15

ãĤ·ãĥ§

0.15

 Rebellion

0.14

Ð¸Ð¼Ñĥ

0.14

 path

0.14

stable

0.14

Activations Density 0.200%

phrases and references related to guidelines and cultural artifacts

No Comments

No Known Activations