INDEX

Explanations

names and positions of individuals in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 mere

-0.15

coop

-0.15

anke

-0.15

urger

-0.14

.ToShort

-0.13

ROSS

-0.13

Ø¬ÙĦ

-0.13

libs

-0.13

 Origins

-0.13

Î¹Î¬

-0.13

POSITIVE LOGITS

CHandle

0.19

:↵↵↵↵↵↵

0.16

.bp

0.15

andal

0.14

uted

0.14

éŁ¿

0.14

 trÃº

0.14

CTest

0.13

 ÐĳÐ¾ÑĢ

0.13

Activations Density 0.075%

names and positions of individuals in professional contexts

No Comments

No Known Activations

names and positions of individuals in professional contexts

No Comments

No Known Activations