INDEX

Explanations

names and titles of individuals, particularly in an academic or professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ansi

-0.15

ory

-0.14

 Wonderland

-0.14

ief

-0.14

ietf

-0.14

StandardItem

-0.14

iman

-0.14

 violation

-0.13

orent

-0.13

leg

-0.13

POSITIVE LOGITS

Ã¤Ã¤

0.15

uby

0.15

 Fant

0.15

Bis

0.14

ÏİÏģÎ±

0.14

CompleteListener

0.14

à¸§à¸ĩ

0.14

LabelText

0.13

Meg

0.13

.MixedReality

0.13

Activations Density 0.004%

names and titles of individuals, particularly in an academic or professional context

No Comments

No Known Activations