INDEX

Explanations

phrases related to performance evaluations or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.20

rint

-0.17

-0.16

igid

-0.15

ximity

-0.15

ibold

-0.14

izon

-0.14

 tack

-0.13

aval

-0.13

sur

-0.13

POSITIVE LOGITS

olson

0.17

urma

0.17

 Byrne

0.15

innie

0.15

stitutions

0.15

atee

0.14

enze

0.14

aac

0.14

Äįas

0.14

Activations Density 0.021%

phrases related to performance evaluations or assessments

No Comments

No Known Activations

phrases related to performance evaluations or assessments

No Comments

No Known Activations