INDEX

Explanations

code-related terms and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ught

-0.15

onders

-0.15

FullYear

-0.14

UGHT

-0.14

bou

-0.14

 ErrorHandler

-0.14

SGlobal

-0.14

uC

-0.14

[right

-0.13

 puss

-0.13

POSITIVE LOGITS

 Cord

0.17

etat

0.16

azer

0.15

illin

0.15

eph

0.15

[{"

0.14

 cord

0.14

 CDDL

0.14

maya

0.14

atters

0.14

Activations Density 0.043%

code-related terms and parameters

No Comments

No Known Activations