INDEX

Explanations

references to hair characteristics and related conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

olo

-0.18

ROLS

-0.17

zzo

-0.15

verte

-0.15

ainment

-0.14

vince

-0.14

fried

-0.14

hire

-0.14

otr

-0.14

otation

-0.14

POSITIVE LOGITS

 follic

0.17

ullet

0.15

xit

0.15

 Collective

0.15

itage

0.15

 tiáº¿t

0.15

vell

0.15

OutputStream

0.15

oucher

0.14

iona

0.14

Activations Density 0.060%

references to hair characteristics and related conditions

No Comments

No Known Activations