INDEX

Explanations

financial metrics and statistical outcomes

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

unsch

-0.15

Ð½Ð¾Ð·

-0.15

UTERS

-0.14

agner

-0.14

PLEX

-0.14

‘

-0.14

norm

-0.14

kova

-0.13

Difficulty

-0.13

zilla

-0.13

POSITIVE LOGITS

(AP

0.19

AP

0.17

 Associated

0.17

akit

0.16

 HRESULT

0.16

Responder

0.15

 Audience

0.15

Associated

0.15

 Autof

0.14

 Anch

0.14

Activations Density 0.275%

financial metrics and statistical outcomes

No Comments

No Known Activations