INDEX

Explanations

token patterns and special characters in code or markup syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ign

-0.16

try

-0.14

 moments

-0.14

 Axel

-0.14

PLIER

-0.14

 lifetime

-0.14

MITTED

-0.14

ÏģÎ¹Î½

-0.14

 Grip

-0.13

 Aires

-0.13

POSITIVE LOGITS

anse

0.15

Ð½Ð´

0.14

ixe

0.14

bob

0.14

ÙĪØ¬

0.14

.cleanup

0.14

agi

0.14

ONG

0.14

Activations Density 0.164%

token patterns and special characters in code or markup syntax

No Comments

No Known Activations