INDEX

Explanations

programming-related terms and operations, particularly those associated with data structures and function calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

undan

-0.14

imon

-0.14

eshire

-0.14

 Realty

-0.13

raq

-0.13

ouch

-0.13

):?>↵

-0.13

aro

-0.13

\n

-0.13

iegel

-0.12

POSITIVE LOGITS

0.17

elib

0.16

éĩĮéĿ¢

0.15

ãĢģãĢģ

0.15

 flor

0.15

isel

0.15

gili

0.14

\_

0.14

 çļĦ

0.14

()->

0.14

Activations Density 0.621%

programming-related terms and operations, particularly those associated with data structures and function calls

No Comments

No Known Activations