INDEX

Explanations

terms related to inquiries or requests for information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

aceous

-0.15

rone

-0.15

witter

-0.14

acher

-0.14

agi

-0.14

sville

-0.14

readcr

-0.14

brit

-0.14

ady

-0.14

POSITIVE LOGITS

 Ð¾ÑĤÐº

0.16

asic

0.15

hoot

0.15

eing

0.15

 Watt

0.14

olib

0.14

asin

0.14

WT

0.14

chor

0.14

 Monte

0.14

Activations Density 0.010%

terms related to inquiries or requests for information

No Comments

No Known Activations