INDEX

Explanations

occurrences of the word "self," which is often used in the context of object-oriented programming

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

arakter

-0.17

pus

-0.16

oard

-0.16

ãĥģãĥ¥

-0.16

itty

-0.16

illas

-0.15

Ars

-0.15

 æ½

-0.14

pcf

-0.14

.Framework

-0.14

POSITIVE LOGITS

0.16

-mÃªme

0.16

ursor

0.15

ivor

0.14

EG

0.14

inox

0.14

insk

0.14

WithData

0.13

asmus

0.13

Activations Density 0.001%

occurrences of the word "self," which is often used in the context of object-oriented programming

No Comments

No Known Activations