INDEX

Explanations

negative qualifiers and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.17

ÑıÑĤÐ¸

-0.16

ken

-0.15

rame

-0.15

addir

-0.14

anter

-0.14

mpar

-0.14

stras

-0.14

ç¤

-0.14

POSITIVE LOGITS

 necessarily

0.17

withstanding

0.16

ANJI

0.15

tingham

0.15

ph

0.15

oday

0.15

imson

0.14

reek

0.14

nes

0.14

Activations Density 0.040%

negative qualifiers and expressions

No Comments

No Known Activations