INDEX

Explanations

references to modifications and changes in policies or complaints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

izia

-0.16

ahi

-0.15

zia

-0.14

abd

-0.13

urat

-0.13

Ø²Ø§

-0.13

ãĤĵãģ¨

-0.13

KHTML

-0.13

 Broadcast

-0.13

POSITIVE LOGITS

ëĿ½

0.14

ellij

0.14

(es

0.14

yw

0.14

ampie

0.14

åħ¬åĳĬ

0.14

hoot

0.14

chte

0.13

rowsable

0.13

Activations Density 0.265%

references to modifications and changes in policies or complaints

No Comments

No Known Activations