INDEX

Explanations

metadata related to media releases 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Å¯v

-0.17

esModule

-0.15

anted

-0.14

 Diary

-0.14

Ð¿ÑĢÐ°Ð²

-0.13

preter

-0.13

vard

-0.13

ãĢħ

-0.13

Ere

-0.13

uming

-0.13

POSITIVE LOGITS

Aw

0.16

ouz

0.15

.scalablytyped

0.15

BuilderInterface

0.15

ê°Ĳ

0.15

atk

0.14

 INTERRUPTION

0.14

ľ´

0.14

awk

0.14

jal

0.13

Activations Density 0.073%

metadata related to media releases and references

No Comments

No Known Activations