INDEX

Explanations

negative phrasing and expressions of doubt or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

nt

-0.17

zelf

-0.14

 INCIDENTAL

-0.14

kontakte

-0.13

ittal

-0.13

CTL

-0.13

ule

-0.13

-caret

-0.13

arc

-0.13

ÄĽk

-0.13

POSITIVE LOGITS

erspective

0.15

ubat

0.14

idente

0.14

acket

0.13

ispens

0.13

/off

0.13

sob

0.13

Ã§e

0.13

epad

0.13

omentum

0.13

Activations Density 0.009%

negative phrasing and expressions of doubt or uncertainty

No Comments

No Known Activations