INDEX

Explanations

strong expressions of agreement or affirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ollar

-0.17

-0.15

icks

-0.15

eps

-0.14

erva

-0.14

oles

-0.14

ulty

-0.14

legate

-0.14

imitives

-0.14

orz

-0.14

POSITIVE LOGITS

 Rena

0.17

ãĥ

0.15

iferay

0.15

nak

0.15

unya

0.14

argent

0.14

nameof

0.14

isks

0.14

ACKET

0.14

ainty

0.13

Activations Density 0.009%

strong expressions of agreement or affirmation

No Comments

No Known Activations