INDEX

Explanations

formatted string literals and placeholders within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.15

ÃŃÅ¡

-0.15

.Op

-0.15

lessly

-0.14

nt

-0.14

cord

-0.14

isz

-0.14

 cord

-0.14

onta

-0.14

sec

-0.14

POSITIVE LOGITS

DataStream

0.20

ylon

0.15

 Webster

0.14

 membr

0.14

bow

0.14

Î½Ïī

0.14

ãģ®ãĤĤ

0.14

ldr

0.14

Neill

0.14

 tÃ½m

0.14

Activations Density 0.005%

formatted string literals and placeholders within code

No Comments

No Known Activations