INDEX

Explanations

references to places, particularly those with cultural or historical significance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

irket

-0.15

dip

-0.15

incinn

-0.15

Dip

-0.15

spi

-0.14

rike

-0.14

anager

-0.14

raki

-0.14

swer

-0.14

enschaft

-0.14

POSITIVE LOGITS

 Ritch

0.16

éŃļ

0.15

ÙĨØ³

0.14

 Schiff

0.14

ingle

0.14

ENTA

0.14

 Plug

0.14

LabelText

0.14

.iso

0.13

une

0.13

Activations Density 0.005%

references to places, particularly those with cultural or historical significance

No Comments

No Known Activations