INDEX

Explanations

comparisons and contrasts between subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

?,?,?,?,

-0.23

$MESS

-0.15

Seven

-0.15

Ø¬Ø§Øª

-0.14

?,?,

-0.14

hiba

-0.14

 MANY

-0.13

-many

-0.13

Î¹ÎºÎ·

-0.13

Ø®Ø±Ùī

-0.13

POSITIVE LOGITS

two

1.10

two

0.93

ä¸¤ä¸ª

0.82

Two

0.80

Two

0.78

TWO

0.78

_two

0.76

-two

0.74

ä¸¤

0.73

 zwei

0.72

Activations Density 0.572%

comparisons and contrasts between subjects

No Comments

No Known Activations