INDEX

Explanations

references to specific products and their associated privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

agara

-0.16

-0.15

iali

-0.14

artin

-0.14

-0.13

 Note

-0.13

Ag

-0.13

imu

-0.13

ience

-0.13

POSITIVE LOGITS

elli

0.15

cue

0.15

deaux

0.15

çĻĤ

0.14

illus

0.14

pls

0.14

XYZ

0.14

tul

0.14

erval

0.14

AFE

0.14

Activations Density 0.071%

references to specific products and their associated privacy policies

No Comments

No Known Activations