INDEX

Explanations

phrases and words indicating difficulty or challenges in various contexts

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

abaj

-0.15

uary

-0.15

STYPE

-0.14

ÙĦÙĬÙĩ

-0.14

isure

-0.14

 pulse

-0.14

Gs

-0.13

lush

-0.13

isi

-0.13

POSITIVE LOGITS

Eid

0.16

ar

0.15

 Hein

0.14

 Snape

0.13

æļ

0.13

igators

0.13

akit

0.13

morph

0.13

Ú¯Ø§ÙĨ

0.13

Activations Density 0.029%

phrases and words indicating difficulty or challenges in various contexts

No Comments

No Known Activations