INDEX

Explanations

phrases that indicate a substance or ingredient's benefits for health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Å¡ak

-0.15

ova

-0.14

ccione

-0.14

CrLf

-0.14

stagram

-0.14

_SB

-0.14

alie

-0.14

oun

-0.14

SY

-0.13

pler

-0.13

POSITIVE LOGITS

eks

0.16

dur

0.15

anford

0.15

uming

0.14

sled

0.14

umer

0.14

Î±Î¹

0.14

emmel

0.14

ãģ°ãģĭãĤĬ

0.14

feof

0.13

Activations Density 0.046%

phrases that indicate a substance or ingredient's benefits for health

No Comments

No Known Activations