INDEX

Explanations

instances where users are prompted to click on links for more information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ubar

-0.17

oon

-0.16

oice

-0.15

ierge

-0.14

outu

-0.14

sonian

-0.14

vely

-0.13

icens

-0.13

mr

-0.13

many

-0.13

POSITIVE LOGITS

for

0.17

ngrx

0.15

ird

0.15

iyan

0.14

.MixedReality

0.14

ehen

0.14

.RELATED

0.13

ÐµÐ·

0.13

elson

0.13

ãĥĥãĥĹ

0.13

Activations Density 0.010%

instances where users are prompted to click on links for more information

No Comments

No Known Activations