INDEX

Explanations

references to significant events and relationships between countries or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

?,?,?,?,

-0.25

OffsetTable

-0.15

hiba

-0.14

$MESS

-0.13

Ø¬Ø§Øª

-0.13

_tF

-0.13

é§ħå¾ĴæŃ©

-0.13

.MixedReality

-0.12

.CustomButton

-0.12

POSITIVE LOGITS

two

1.34

two

1.12

Two

1.02

TWO

1.01

Two

0.95

-two

0.93

_two

0.92

ä¸¤ä¸ª

0.90

 deux

0.88

.two

0.88

Activations Density 1.096%

references to significant events and relationships between countries or entities

No Comments

No Known Activations