INDEX

Explanations

ownership and possessive language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

runner

-0.18

Ð»Ð°Ð²

-0.16

ÏĢÎ¬

-0.15

Runner

-0.15

 Runner

-0.14

 Rede

-0.14

CLR

-0.14

roads

-0.14

Router

-0.14

xor

-0.14

POSITIVE LOGITS

 right

0.91

right

0.73

 Right

0.69

-right

0.69

_right

0.67

Right

0.66

 RIGHT

0.66

.right

0.64

	right

0.60

åı³

0.55

Activations Density 0.235%

ownership and possessive language

No Comments

No Known Activations