INDEX

Explanations

preferences and priorities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

tep

-0.15

witter

-0.15

ÑĢÐ¸Ñģ

-0.15

ëĨ

-0.15

BOTTOM

-0.15

iguiente

-0.14

roupon

-0.14

eyse

-0.14

 há»¯u

-0.14

omik

-0.14

POSITIVE LOGITS

 prefer

1.10

 preference

1.10

 preferred

0.97

 preferences

0.95

 Preference

0.94

 Prefer

0.94

 prefers

0.90

prefer

0.90

Preference

0.84

 Preferred

0.82

Activations Density 0.584%

preferences and priorities in various contexts

No Comments

No Known Activations