INDEX

Explanations

possessive forms denoting ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

sworth

-0.18

-0.17

kill

-0.17

omid

-0.16

ksen

-0.15

ÐĴÑĤ

-0.14

hoot

-0.14

tle

-0.14

unar

-0.14

Ø±Ø³ÛĮ

-0.14

POSITIVE LOGITS

asti

0.15

agine

0.14

achuset

0.14

SSID

0.14

ÂĢÂĻ

0.14

Ã¤nn

0.14

ancer

0.14

 ÑĥÑĩÐ°Ñģ

0.14

quist

0.13

 gonna

0.13

Activations Density 0.143%

possessive forms denoting ownership

No Comments

No Known Activations

possessive forms denoting ownership

No Comments

No Known Activations