INDEX

Explanations

references to legal authority and jurisdiction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

tle

-0.19

apan

-0.18

op

-0.15

IP

-0.15

ery

-0.14

nik

-0.14

 Char

-0.14

chin

-0.14

_CONST

-0.14

aat

-0.14

POSITIVE LOGITS

OfFile

0.16

¶Į

0.16

TEGER

0.15

.setResult

0.15

ByVersion

0.15

Ã±ana

0.15

activex

0.14

semble

0.14

addtogroup

0.14

lyph

0.14

Activations Density 0.012%

references to legal authority and jurisdiction

No Comments

No Known Activations