INDEX

Explanations

references to responsibilities or obligations, particularly in a formal or legal context

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

 Darling

-0.16

sto

-0.15

adia

-0.15

eur

-0.15

-scale

-0.14

Ws

-0.14

oon

-0.14

naissance

-0.14

atters

-0.14

POSITIVE LOGITS

iful

0.19

odesk

0.16

fully

0.16

uble

0.15

½æķ°

0.15

 äºİ

0.15

 performed

0.15

ful

0.15

inky

0.15

daÅŁ

0.14

Activations Density 0.012%

references to responsibilities or obligations, particularly in a formal or legal context

No Comments

No Known Activations