INDEX

Explanations

mentions of badgers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ald

-0.17

ument

-0.17

adol

-0.15

uml

-0.15

createView

-0.15

izu

-0.15

lef

-0.14

alach

-0.14

aleza

-0.14

Mess

-0.14

POSITIVE LOGITS

avou

0.16

.Axis

0.15

kov

0.15

Äį

0.15

Cly

0.14

avra

0.14

Ty

0.14

 Hipp

0.14

rÃ³

0.13

ubl

0.13

Activations Density 0.005%

mentions of badgers in various contexts

No Comments

No Known Activations