INDEX

Explanations

specific formatting or patterns in citations 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

_BUSY

-0.15

-0.14

.Gradient

-0.14

igne

-0.14

plx

-0.13

çļĦäºĭ

-0.13

ample

-0.13

èªĮ

-0.13

ptest

-0.13

 competit

-0.13

POSITIVE LOGITS

 Jaune

0.14

OptionsResolver

0.14

/č↵

0.14

annya

0.14

 Incontri

0.14

-ÐŁÐµÑĤÐµÑĢÐ±

0.14

andler

0.13

 intr

0.13

orent

0.13

LPARAM

0.13

Activations Density 0.001%

specific formatting or patterns in citations and references

No Comments

No Known Activations