INDEX

Explanations

instances of entities or actions related to removal, dismissal, or exit

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.16

ither

-0.15

ulings

-0.14

erras

-0.14

imus

-0.14

äºŃ

-0.14

invisible

-0.14

 Harmony

-0.14

UES

-0.14

_missing

-0.13

POSITIVE LOGITS

_EXISTS

0.16

ãĤ´ãĥª

0.15

urger

0.15

Dot

0.14

CKER

0.14

orget

0.14

odore

0.14

ematic

0.13

Ã´i

0.13

NOP

0.13

Activations Density 0.114%

instances of entities or actions related to removal, dismissal, or exit

No Comments

No Known Activations