INDEX

Explanations

mentions of places, establishments, or locations in context to activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ersh

-0.18

ovol

-0.16

swick

-0.15

croft

-0.15

çĴ°

-0.15

Ð¾Ð»Ð¶

-0.14

tam

-0.14

irable

-0.14

eld

-0.14

 witnesses

-0.14

POSITIVE LOGITS

efa

0.16

Ã¨ge

0.15

crets

0.15

ennen

0.15

PERT

0.15

å®ĩ

0.13

nie

0.13

otos

0.13

quia

0.13

Ð»Ð»

0.13

Activations Density 0.579%

mentions of places, establishments, or locations in context to activities or events

No Comments

No Known Activations