INDEX

Explanations

citations and references to studies or data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

AQ

-0.16

ept

-0.16

¢åįķ

-0.15

OOM

-0.15

Ãµi

-0.15

axter

-0.14

ither

-0.14

alfa

-0.14

orz

-0.14

oom

-0.14

POSITIVE LOGITS

ALSE

0.15

ÂłPS

0.14

CLR

0.14

CSV

0.14

JS

0.14

 ÑĤÐ²Ð°

0.14

åħį

0.14

SS

0.14

rientation

0.13

Activations Density 0.039%

citations and references to studies or data

No Comments

No Known Activations