INDEX

Explanations

symbols and punctuation marks in code or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

oy

-0.15

aland

-0.15

allas

-0.15

fel

-0.14

ulen

-0.14

ignon

-0.14

borg

-0.14

olit

-0.14

olynomial

-0.14

ilk

-0.14

POSITIVE LOGITS

aira

0.15

 Strikes

0.14

hek

0.14

Corner

0.14

 thá»§y

0.14

dirty

0.14

VS

0.14

ÎµÏģÎ¿

0.14

 Dirty

0.14

0.13

Activations Density 0.017%

symbols and punctuation marks in code or programming contexts

No Comments

No Known Activations