INDEX

Explanations

mentions of locations or places where significant events or activities occur

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

cene

-0.18

.TXT

-0.16

uxe

-0.15

Charsets

-0.15

ellar

-0.15

arge

-0.14

áº§m

-0.14

Ã¥r

-0.14

 nackte

-0.14

 åĨĨ

-0.14

POSITIVE LOGITS

(s

0.18

åĢĳ

0.17

ses

0.16

sand

0.16

[s

0.15

oni

0.15

oom

0.15

airs

0.14

åłĤ

0.14

 ministries

0.14

Activations Density 0.915%

mentions of locations or places where significant events or activities occur

No Comments

No Known Activations