INDEX

Explanations

phrases expressing temporal relationships and prompts for action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ppv

-0.19

uil

-0.18

quo

-0.17

-deals

-0.16

ogh

-0.15

_Des

-0.15

 Rounds

-0.14

DebugEnabled

-0.14

kv

-0.14

marsh

-0.14

POSITIVE LOGITS

agger

0.18

ober

0.16

avern

0.15

aramel

0.15

Mol

0.14

arily

0.14

ing

0.14

adas

0.14

acker

0.13

ason

0.13

Activations Density 0.002%

phrases expressing temporal relationships and prompts for action

No Comments

No Known Activations