INDEX

Explanations

references to charities and charitable organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oe

-0.17

uits

-0.15

lies

-0.15

HELL

-0.15

erb

-0.15

ils

-0.14

 Murphy

-0.14

ii

-0.14

RIORITY

-0.14

lis

-0.14

POSITIVE LOGITS

Ø§ÙĨ

0.15

VarChar

0.15

UPER

0.14

TEGER

0.14

andom

0.14

ector

0.14

odega

0.14

ware

0.14

 Buccane

0.14

 CircularProgress

0.13

Activations Density 0.015%

references to charities and charitable organizations

No Comments

No Known Activations