INDEX

Explanations

references to various types of dresses and fashion-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

lemn

-0.18

à¥Įà¤Ł

-0.15

ensis

-0.15

Ì§

-0.15

.UR

-0.14

Dag

-0.14

antz

-0.14

esel

-0.14

 Pitch

-0.14

quia

-0.14

POSITIVE LOGITS

IDEO

0.15

egt

0.14

ega

0.14

lifetime

0.14

ablish

0.14

aus

0.14

 âĸ²

0.14

anko

0.14

blade

0.13

utex

0.13

Activations Density 0.032%

references to various types of dresses and fashion-related terms

No Comments

No Known Activations