INDEX

Explanations

references to specific names or entities, particularly in relation to cultural or historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

izontally

-0.14

Ã©sz

-0.14

stru

-0.14

hait

-0.14

moduleId

-0.14

pector

-0.14

yster

-0.14

AVC

-0.13

argent

-0.13

mpl

-0.13

POSITIVE LOGITS

ropolis

0.20

emiah

0.19

laces

0.18

flix

0.17

odem

0.15

theless

0.15

otic

0.15

fully

0.15

ending

0.15

Ne

0.15

Activations Density 0.033%

references to specific names or entities, particularly in relation to cultural or historical contexts

No Comments

No Known Activations