INDEX

Explanations

inquiries or questions related to advice and recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Hel

-0.16

hel

-0.15

 Merrill

-0.15

SEC

-0.14

mw

-0.14

 Barth

-0.14

itational

-0.14

quam

-0.14

secs

-0.14

PLE

-0.14

POSITIVE LOGITS

0.17

_runner

0.16

?}",

0.15

uges

0.14

.tech

0.14

mÃ¡

0.14

XObject

0.14

(inst

0.13

_IE

0.13

Activations Density 0.065%

inquiries or questions related to advice and recommendations

No Comments

No Known Activations