INDEX

Explanations

references to geographical locations and their political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

_Tis

-0.16

strup

-0.16

rick

-0.16

resi

-0.14

.docker

-0.14

cesso

-0.14

_mC

-0.14

inan

-0.14

otte

-0.14

asaki

-0.13

POSITIVE LOGITS

iced

0.15

sad

0.15

ÑĢÑĥÐ¶

0.14

 fold

0.13

non

0.13

ched

0.13

Lyn

0.13

Zub

0.13

lyn

0.13

 zast

0.13

Activations Density 0.026%

references to geographical locations and their political contexts

No Comments

No Known Activations