INDEX

Explanations

the structure of test cases or assertions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

acier

-0.17

lick

-0.16

bih

-0.16

apg

-0.15

ondon

-0.15

ewire

-0.15

eness

-0.15

ITERAL

-0.15

elves

-0.15

mong

-0.14

POSITIVE LOGITS

lim

0.16

Extras

0.15

ison

0.15

çĲĨ

0.14

acons

0.14

Éµ

0.14

 Ivanka

0.14

 ambient

0.14

lim

0.14

Activations Density 0.017%

the structure of test cases or assertions in code

No Comments

No Known Activations