INDEX

Explanations

references to demographic statistics or data points related to individuals and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

orre

-0.15

 AtatÃ¼rk

-0.14

Ð²Ð°Ð¶Ð°

-0.14

taÅŁ

-0.14

aits

-0.14

tay

-0.14

eru

-0.13

riger

-0.13

 intros

-0.13

æħ¶

-0.13

POSITIVE LOGITS

 finally

0.15

utin

0.15

ahl

0.14

 Ridley

0.14

isses

0.14

ÑĢÐ¾Ð²Ð°

0.14

 RuntimeObject

0.13

↵

0.13

_tF

0.13

↵↵

0.13

Activations Density 0.144%

references to demographic statistics or data points related to individuals and their attributes

No Comments

No Known Activations