INDEX

Explanations

information related to job interviews and candidate evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 spou

-0.14

amba

-0.14

ustos

-0.14

à¸´à¸Ī

-0.13

efs

-0.13

ascus

-0.13

isÃŃ

-0.13

ÑĢÐ¸Ð·

-0.13

ibile

-0.13

áº·p

-0.13

POSITIVE LOGITS

 perform

0.65

 performs

0.61

 performing

0.61

perform

0.60

Perform

0.56

 performed

0.56

 Perform

0.56

 Performing

0.51

 fare

0.48

 performer

0.47

Activations Density 0.191%

information related to job interviews and candidate evaluations

No Comments

No Known Activations