INDEX

Explanations

references to readers and audience engagement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ux

-0.17

alan

-0.16

resses

-0.16

oken

-0.16

orm

-0.16

gre

-0.16

ech

-0.15

ard

-0.15

sWith

-0.15

avor

-0.15

POSITIVE LOGITS

hip

0.31

hood

0.20

/view

0.20

hips

0.19

Ã¨le

0.19

/users

0.19

/list

0.19

fare

0.18

/client

0.18

/customer

0.18

Activations Density 0.103%

references to readers and audience engagement in various contexts

No Comments

No Known Activations