INDEX

Explanations

code-related elements and structures, especially those pertaining to class and method definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

irie

-0.21

 Trace

-0.17

 TRACE

-0.15

ouch

-0.15

owl

-0.15

oste

-0.15

owe

-0.15

eprom

-0.14

vice

-0.14

acias

-0.14

POSITIVE LOGITS

æģ¯

0.15

åĲ¾

0.14

asal

0.14

(_:

0.14

 cages

0.13

antas

0.13

ãģªãĤĵãģ¦

0.13

 ÙĦÙĤ

0.13

PFN

0.13

Elite

0.13

Activations Density 0.008%

code-related elements and structures, especially those pertaining to class and method definitions

No Comments

No Known Activations