INDEX

Explanations

instances of lists or sequences, especially those punctuated by commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 indeed

-0.17

-0.15

 thus

-0.13

åıĬåħ¶

-0.13

/or

-0.13

 Indeed

-0.13

oba

-0.13

-loaded

-0.13

 bÃ¶ylece

-0.13

POSITIVE LOGITS

iffies

0.15

cken

0.15

lsru

0.14

Ã³ng

0.14

 ÑĢÐ°Ð·Ð°

0.14

ftware

0.14

(?)

0.13

bsites

0.13

ordes

0.13

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.13

Activations Density 0.145%

instances of lists or sequences, especially those punctuated by commas

No Comments

No Known Activations