INDEX

Explanations

information related to availability and location of resources or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

umont

-0.15

ãĥ³ãĥģ

-0.14

é¢Ĩ

-0.14

idar

-0.14

upo

-0.14

enco

-0.14

ador

-0.14

krom

-0.14

($.

-0.13

outu

-0.13

POSITIVE LOGITS

ï¼Īå¹³æĪĲ

0.16

urg

0.15

gest

0.15

odon

0.14

 Foley

0.14

solete

0.14

á»ĩ

0.14

 grav

0.14

Ð¸Ñİ

0.13

Activations Density 0.008%

information related to availability and location of resources or individuals

No Comments

No Known Activations