INDEX

Explanations

phrases related to access or availability of resources

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

rys

-0.15

ickets

-0.14

oppers

-0.14

Î½Î±Î½

-0.13

warts

-0.13

 ÐĵÐ¾Ð»

-0.13

agan

-0.13

opp

-0.13

 reuseIdentifier

-0.13

omas

-0.13

POSITIVE LOGITS

0.18

eyse

0.16

ORY

0.14

rary

0.14

ichert

0.14

UInteger

0.14

Äįe

0.14

Uvs

0.14

Charsets

0.13

Activations Density 0.049%

phrases related to access or availability of resources

No Comments

No Known Activations