INDEX

Explanations

negations and expressions of rejection or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.16

etri

-0.16

 Banc

-0.15

tej

-0.15

ucci

-0.15

alm

-0.15

ÙĬØ§Øª

-0.14

ï¼ĪæĺŃåĴĮ

-0.14

utz

-0.14

lobby

-0.14

POSITIVE LOGITS

 necessarily

0.16

0.14

riger

0.14

[@

0.14

 bare

0.14

LEAR

0.14

-original

0.13

 Universities

0.13

 Alternative

0.13

Tw

0.13

Activations Density 0.039%

negations and expressions of rejection or absence

No Comments

No Known Activations