INDEX

Explanations

technical programming terms and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 <!--[

-0.15

uv

-0.14

unter

-0.14

Ø±ÛĮÚ©

-0.14

incr

-0.14

unte

-0.14

ino

-0.13

à¥Ŀ

-0.13

als

-0.13

 interven

-0.13

POSITIVE LOGITS

 import

1.05

 Import

0.94

-import

0.89

import

0.88

 imports

0.86

Import

0.85

 IMPORT

0.84

 importing

0.84

_import

0.82

.import

0.82

Activations Density 0.053%

technical programming terms and references

No Comments

No Known Activations