INDEX

Explanations

references to company names and legal entities

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

-0.16

ÑĥÑģÑĤ

-0.15

uer

-0.15

oir

-0.14

yz

-0.13

ives

-0.13

ilio

-0.13

oure

-0.13

pread

-0.13

INCT

-0.13

POSITIVE LOGITS

evi

0.16

ataka

0.16

'gc

0.15

HeaderValue

0.14

anked

0.14

ugins

0.14

isky

0.14

(æ°´

0.14

ungeon

0.13

isku

0.13

Activations Density 0.021%

references to company names and legal entities

No Comments

No Known Activations