INDEX

Explanations

numerical data related to statistics and rates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

heimer

-0.17

ifold

-0.17

ÌĨ

-0.15

abcdefghijkl

-0.14

.rpm

-0.14

CodeGen

-0.14

rud

-0.14

º

-0.14

typings

-0.14

vsp

-0.14

POSITIVE LOGITS

onom

0.18

cents

0.16

inp

0.15

RC

0.15

á»ĳn

0.15

 indice

0.14

 forks

0.14

 conc

0.14

 hundred

0.14

Activations Density 0.036%

numerical data related to statistics and rates

No Comments

No Known Activations