INDEX

Explanations

numerical values and references to specific identifiers or codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

CTS

-0.15

arget

-0.15

/sys

-0.15

rag

-0.14

ragon

-0.14

dux

-0.14

peat

-0.14

 ìļ©

-0.14

subs

-0.14

uet

-0.13

POSITIVE LOGITS

chw

0.15

 ../../../

0.14

Ð½ÑĸÑģÑĤ

0.14

AlmostEqual

0.14

sing

0.14

atatype

0.14

_pix

0.14

entanyl

0.13

.YesNo

0.13

 hoop

0.13

Activations Density 0.011%

numerical values and references to specific identifiers or codes

No Comments

No Known Activations