INDEX

Explanations

references to positive qualities or endorsements associated with products or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

istrovstvÃŃ

-0.21

iphertext

-0.18

ernote

-0.15

oire

-0.15

vertisement

-0.15

 duty

-0.14

pedo

-0.14

swire

-0.14

EDIUM

-0.14

è¿«

-0.14

POSITIVE LOGITS

_utilities

0.15

upe

0.15

 wand

0.15

apos

0.14

ough

0.14

ware

0.13

 Lund

0.13

 refinement

0.13

vas

0.13

/-

0.13

Activations Density 0.053%

references to positive qualities or endorsements associated with products or experiences

No Comments

No Known Activations