INDEX

Explanations

phrases relating to legal disclaimers and professional advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Democracy

-0.16

DEM

-0.16

 Visibility

-0.15

LTE

-0.15

 Democr

-0.15

LC

-0.15

å½

-0.15

arp

-0.15

 HÃ²a

-0.15

 Lois

-0.15

POSITIVE LOGITS

 reliance

0.20

Drv

0.15

UNUSED

0.15

forman

0.15

Ú¯Ø§ÙĨ

0.15

 Viewer

0.15

 relied

0.15

eneral

0.15

hread

0.15

AndView

0.15

Activations Density 0.034%

phrases relating to legal disclaimers and professional advice

No Comments

No Known Activations