INDEX

Explanations

phrases indicating statements or assertions, particularly those starting with "it is said" and their variations

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

-0.17

ustil

-0.16

polator

-0.15

roe

-0.15

iais

-0.14

esser

-0.14

Ð·Ð½Ð°Ñĩ

-0.14

ampie

-0.14

UniformLocation

-0.14

.PR

-0.13

POSITIVE LOGITS

_PD

0.15

ss

0.15

avy

0.14

SAT

0.14

TED

0.14

iment

0.14

 vener

0.14

mand

0.14

URN

0.14

ADI

0.13

Activations Density 0.016%

phrases indicating statements or assertions, particularly those starting with "it is said" and their variations

No Comments

No Known Activations