INDEX

Explanations

phrases that indicate community-based initiatives or activities

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

enberg

-0.16

ÐĶÐļ

-0.15

gh

-0.15

Jah

-0.14

arrow

-0.14

size

-0.14

 Bord

-0.14

gen

-0.14

lining

-0.14

do

-0.14

POSITIVE LOGITS

agini

0.17

 infix

0.16

abus

0.15

fuel

0.15

ARAM

0.15

nable

0.15

 åĨĨ

0.15

.LogWarning

0.14

away

0.14

agli

0.14

Activations Density 0.014%

phrases that indicate community-based initiatives or activities

No Comments

No Known Activations