INDEX

Explanations

references to geographical locations and regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.15

ersen

-0.14

 ours

-0.14

ÑıÑħ

-0.14

normal

-0.13

Normal

-0.13

hoff

-0.13

arded

-0.13

Program

-0.13

eled

-0.13

POSITIVE LOGITS

 Arbor

0.15

otel

0.15

ube

0.15

AtA

0.14

/templates

0.14

,strlen

0.13

VarChar

0.13

BuilderInterface

0.13

UBE

0.13

 Tarihi

0.13

Activations Density 0.001%

references to geographical locations and regions

No Comments

No Known Activations