INDEX

Explanations

references to academic and professional achievements in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

asso

-0.16

structuring

-0.15

Scaler

-0.15

ity

-0.14

arov

-0.14

resa

-0.14

ultan

-0.14

ÑĦÐµÑĢ

-0.14

cry

-0.13

teenth

-0.13

POSITIVE LOGITS

TD

0.15

_stat

0.15

odium

0.15

pts

0.14

tml

0.14

 Mine

0.14

onds

0.14

_scheme

0.14

Stat

0.13

ghi

0.13

Activations Density 0.567%

references to academic and professional achievements in various fields

No Comments

No Known Activations