INDEX

Explanations

emotional or descriptive adjectives and associated terms that signify support or recognition of entities

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

NIL

-0.18

Dot

-0.17

Dot

-0.16

oka

-0.14

dot

-0.14

ransition

-0.14

jest

-0.14

_dot

-0.14

 Demon

-0.14

cie

-0.13

POSITIVE LOGITS

iento

0.15

gle

0.15

uld

0.15

eri

0.15

igm

0.15

.Byte

0.14

erti

0.14

ULD

0.14

adder

0.14

xAC

0.14

Activations Density 0.060%

emotional or descriptive adjectives and associated terms that signify support or recognition of entities

No Comments

No Known Activations