INDEX

Explanations

specific geographical locations and associated stories or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

elly

-0.14

rezent

-0.14

PIO

-0.14

ully

-0.14

ãĤ¸ãĤª

-0.14

Ĥæķ°

-0.13

 KrÃ¡l

-0.13

arella

-0.13

xac

-0.13

èī

-0.13

POSITIVE LOGITS

md

0.14

Ath

0.14

ļ

0.14

ondere

0.14

 Doll

0.13

uche

0.13

ayed

0.13

 doll

0.13

platz

0.13

erves

0.13

Activations Density 0.023%

specific geographical locations and associated stories or context

No Comments

No Known Activations