INDEX

Explanations

programming-related commands and functions 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olet

-0.17

 coron

-0.15

kÃ¼n

-0.15

sap

-0.14

uet

-0.14

eton

-0.13

.gca

-0.13

opes

-0.13

Ĳ

-0.13

bew

-0.13

POSITIVE LOGITS

.mk

0.18

$(

0.17

 targets

0.17

idon

0.17

VP

0.17

($(

0.17

clean

0.17

à¸±à¸Ļà¸¢

0.16

.SE

0.16

 Targets

0.16

Activations Density 0.030%

programming-related commands and functions in code snippets

No Comments

No Known Activations