INDEX

Explanations

bullet points or list items that describe services or offerings

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

acin

-0.16

reau

-0.16

_ck

-0.15

nf

-0.15

ìķ¼

-0.15

nout

-0.15

/WebAPI

-0.14

iÄįe

-0.14

èĩ£

-0.14

aker

-0.14

POSITIVE LOGITS

bsites

0.16

Ã¡cil

0.14

orro

0.14

 conceived

0.14

obody

0.13

itten

0.13

 conception

0.13

éİ

0.13

olet

0.13

Activations Density 0.023%

bullet points or list items that describe services or offerings

No Comments

No Known Activations