INDEX

Explanations

names and titles related to authority, organizations, or formal entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Pistol

-0.15

 establishment

-0.15

.backends

-0.15

ceipt

-0.14

oven

-0.14

ÑģÐ¸Ð¾Ð½

-0.14

-cap

-0.14

 cann

-0.14

bo

-0.13

POSITIVE LOGITS

COPE

0.15

 Shir

0.15

iya

0.15

ìĭ¬

0.14

 Ð²Ð½Ñĥ

0.14

umlu

0.14

exercise

0.13

Rnd

0.13

seat

0.13

achine

0.13

Activations Density 0.039%

names and titles related to authority, organizations, or formal entities

No Comments

No Known Activations