INDEX

Explanations

programming syntax and structure in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÙĪØ¯Ùĩ

-0.18

 constexpr

-0.15

ÐºÐµÑĤ

-0.15

Ø§Ø²Ùĩ

-0.15

ãĤ

-0.14

gib

-0.14

lobal

-0.14

æŀ

-0.14

-0.13

chrift

-0.13

POSITIVE LOGITS

 string

0.19

 String

0.18

 Option

0.17

int

0.16

acam

0.15

 option

0.15

IGH

0.14

Ð¾ÑĤÑĢÐµÐ±

0.14

 Immigration

0.14

ossier

0.14

Activations Density 0.010%

programming syntax and structure in code snippets

No Comments

No Known Activations