INDEX

Explanations

conditional statements in code

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

acob

-0.15

gett

-0.15

WithEmail

-0.14

ÑģÐ¾Ð²

-0.14

_gradients

-0.14

opal

-0.14

rtl

-0.14

omanip

-0.14

-0.13

gow

-0.13

POSITIVE LOGITS

atum

0.16

dum

0.15

USR

0.15

 DECL

0.14

oden

0.14

ymb

0.14

tors

0.14

 Ð±Ð¾Ð»Ð¸

0.13

illas

0.13

odian

0.13

Activations Density 0.087%

conditional statements in code

No Comments

No Known Activations