INDEX

Explanations

negative phrases or qualifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

oyer

-0.15

uffman

-0.15

inds

-0.15

ll

-0.15

uby

-0.15

umes

-0.15

igon

-0.14

çģ¯

-0.14

ymph

-0.14

ights

-0.14

POSITIVE LOGITS

unta

0.18

elda

0.16

ÑĨÐµÑĢ

0.15

ceae

0.15

Wet

0.15

AbsolutePath

0.14

ammad

0.14

ÏĨÎ¿

0.14

-addons

0.14

StackSize

0.14

Activations Density 0.002%

negative phrases or qualifiers

No Comments

No Known Activations