INDEX

Explanations

references to functions and callbacks in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Éµ

-0.16

ÑĢÐ¾Ñĩ

-0.15

tah

-0.15

Ø§ÛĮØ´

-0.14

amen

-0.14

ein

-0.14

meer

-0.14

 preferredStyle

-0.14

pong

-0.14

barang

-0.14

POSITIVE LOGITS

isiyle

0.16

illaume

0.16

auen

0.15

lint

0.15

æ¼

0.15

fw

0.14

 polling

0.14

stage

0.13

 Kurulu

0.13

lt

0.13

Activations Density 0.162%

references to functions and callbacks in programming contexts

No Comments

No Known Activations