INDEX

Explanations

references to quantifiers and vague terms related to amounts and frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

tri

-0.16

zin

-0.14

avis

-0.14

çĸ

-0.14

avage

-0.14

Ð½ÐµÐ²

-0.14

 Chad

-0.14

 OpCode

-0.14

 syst

-0.13

exh

-0.13

POSITIVE LOGITS

ãĤ¹ãĥĨãĤ£

0.17

resco

0.15

æĭ¿

0.15

lady

0.15

 ActiveForm

0.15

Ã©ment

0.15

ivant

0.15

diff

0.14

afc

0.14

ÑĢÑı

0.14

Activations Density 0.077%

references to quantifiers and vague terms related to amounts and frequency

No Comments

No Known Activations