INDEX

Explanations

references to "Gad" and its variations or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-toggler

-0.18

Brain

-0.15

ctl

-0.15

dispose

-0.15

enan

-0.15

inger

-0.14

opsy

-0.14

erten

-0.14

vendors

-0.14

entiful

-0.14

POSITIVE LOGITS

olin

0.20

gad

0.19

ient

0.18

gets

0.17

ets

0.16

tics

0.16

Gad

0.16

adlo

0.15

luet

0.15

ially

0.15

Activations Density 0.018%

references to "Gad" and its variations or related concepts

No Comments

No Known Activations