INDEX

Explanations

programming-related methods and functions for iterating over collections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Uhr

-0.17

gent

-0.16

omain

-0.16

 sana

-0.16

otti

-0.16

rica

-0.15

 Somerset

-0.15

arken

-0.15

Ney

-0.15

kia

-0.15

POSITIVE LOGITS

icone

0.15

ardown

0.15

RODUCTION

0.14

ÏİÎ½Î±

0.14

ergy

0.14

Unused

0.14

unfinished

0.14

DidLoad

0.14

 aÃ§Ä±

0.13

 âĢı

0.13

Activations Density 0.030%

programming-related methods and functions for iterating over collections

No Comments

No Known Activations