INDEX

Explanations

directional phrases and references related to location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 strstr

-0.15

ative

-0.15

 glGet

-0.14

rado

-0.14

amoto

-0.14

eli

-0.14

isko

-0.14

oku

-0.13

atis

-0.13

ffe

-0.13

POSITIVE LOGITS

usb

0.15

 omas

0.15

ials

0.14

plorer

0.14

Ð»Ð°Ð½

0.14

Æł

0.14

['__

0.13

istrar

0.13

ÙĪÙģ

0.13

gil

0.13

Activations Density 0.030%

directional phrases and references related to location

No Comments

No Known Activations