INDEX

Explanations

references to line numbers in code or error messages

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ovich

-0.17

£

-0.15

oser

-0.15

alle

-0.15

oga

-0.14

ANA

-0.14

 sana

-0.14

Ã´ng

-0.14

 Gauge

-0.14

 Ivory

-0.14

POSITIVE LOGITS

uri

0.15

kla

0.15

SFML

0.15

ãĥ³ãĥĸ

0.15

untime

0.14

rug

0.14

 Pemb

0.14

æĬľ

0.14

Activations Density 0.029%

references to line numbers in code or error messages

No Comments

No Known Activations