INDEX

Explanations

military units and commands

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

zdy

-0.17

anca

-0.15

uito

-0.15

ignon

-0.15

ategories

-0.14

ROME

-0.14

zsche

-0.14

 stopwatch

-0.14

jedn

-0.14

Ð¾Ð³Ð°

-0.14

POSITIVE LOGITS

 Granite

0.15

0.14

 plÃ¡

0.14

 Mobile

0.14

oz

0.14

 Sawyer

0.14

Fur

0.13

 Orth

0.13

 ÐĹÐ°Ð²

0.13

Activations Density 0.027%

military units and commands

No Comments

No Known Activations