INDEX

Explanations

specific names or terms that refer to people or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

hurst

-0.16

&&&&

-0.15

izard

-0.15

afen

-0.14

addy

-0.14

hof

-0.14

ifton

-0.14

eddar

-0.14

hevik

-0.14

lint

-0.14

POSITIVE LOGITS

ucc

0.17

REW

0.16

 Richards

0.15

 tart

0.15

val

0.15

 diff

0.14

fog

0.14

 mond

0.14

Dag

0.14

essel

0.14

Activations Density 0.003%

specific names or terms that refer to people or characters

No Comments

No Known Activations