INDEX

Explanations

large numerical values or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 workings

-0.16

ro

-0.16

bullet

-0.15

-0.14

oa

-0.14

etri

-0.14

lah

-0.13

 Answers

-0.13

POSITIVE LOGITS

akis

0.16

.magic

0.16

atty

0.14

uuid

0.14

beros

0.13

samp

0.13

chein

0.13

erras

0.13

ìłĪ

0.13

Activations Density 0.042%

large numerical values or identifiers

No Comments

No Known Activations