INDEX

Explanations

historical references to military events or services

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

deaux

-0.19

kinson

-0.17

gger

-0.17

.office

-0.16

vangst

-0.16

ãĥĥãĥī

-0.16

Ã§ak

-0.15

Ð»Ð¾Ð´

-0.15

ean

-0.15

 serialVersionUID

-0.15

POSITIVE LOGITS

 exact

0.17

Ã¶

0.17

 Casc

0.16

 history

0.16

 Bart

0.15

 level

0.15

ipt

0.14

Mug

0.14

few

0.14

Activations Density 0.234%

historical references to military events or services

No Comments

No Known Activations