INDEX

Explanations

phrases that indicate significant actions or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

NotSupportedException

-0.16

PU

-0.16

tip

-0.14

 Pessoa

-0.14

PRS

-0.14

osen

-0.14

apos

-0.14

.Dispatch

-0.14

allas

-0.13

POSITIVE LOGITS

-Cs

0.17

ibern

0.16

REET

0.16

zk

0.15

isd

0.15

Ð»ÑıÐ´

0.14

ingu

0.14

åĴ²

0.14

tÃ©

0.14

itter

0.14

Activations Density 0.011%

phrases that indicate significant actions or conditions

No Comments

No Known Activations