INDEX

Explanations

terms and phrases related to support and access within 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

akest

-0.16

ovie

-0.15

hook

-0.15

readcr

-0.15

emies

-0.15

adt

-0.15

ione

-0.14

hread

-0.14

ories

-0.14

radi

-0.14

POSITIVE LOGITS

zb

0.14

iset

0.14

 ÙĤØ§ÙĦ

0.13

à¹Ĥà¸Ľà¸£

0.13

zf

0.13

 Nach

0.13

YRO

0.13

.cat

0.13

yte

0.13

cro

0.12

Activations Density 0.008%

terms and phrases related to support and access within various contexts

No Comments

No Known Activations