INDEX

Explanations

references to differences and diversity 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

jure

-0.16

chang

-0.15

rary

-0.15

lier

-0.14

osa

-0.14

orden

-0.14

peare

-0.14

 Bart

-0.14

itle

-0.13

POSITIVE LOGITS

 respective

0.20

 nhau

0.19

 approaches

0.18

 experience

0.17

 styles

0.16

 interpre

0.16

 respectively

0.15

 interpretation

0.15

-shaped

0.15

 approach

0.15

Activations Density 0.142%

references to differences and diversity in various contexts

No Comments

No Known Activations