INDEX

Explanations

references to HTTP response statuses and related data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rogen

-0.15

ition

-0.15

self

-0.15

 Gros

-0.14

 premises

-0.14

 cred

-0.14

oya

-0.14

roperty

-0.14

qi

-0.14

ÑĤÐµÑģÑĮ

-0.14

POSITIVE LOGITS

ourcem

0.16

ozo

0.16

yh

0.15

yonel

0.15

eydi

0.15

¢ħ

0.15

gia

0.15

alist

0.15

à¥ī

0.15

0.14

Activations Density 0.021%

references to HTTP response statuses and related data

No Comments

No Known Activations