INDEX

Explanations

references to a specific brand or product name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

utf

-0.14

onu

-0.14

ex

-0.14

uci

-0.14

olis

-0.14

feeding

-0.14

áº¡c

-0.14

ocking

-0.14

ByUrl

-0.13

 NotImplementedException

-0.13

POSITIVE LOGITS

ouser

0.19

lobal

0.17

ungen

0.17

sak

0.17

acerb

0.16

LEGRO

0.16

unger

0.15

inho

0.15

nger

0.15

baugh

0.14

Activations Density 0.027%

references to a specific brand or product name

No Comments

No Known Activations