INDEX

Explanations

markers for data retrieval or citation references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

GetObject

-0.15

íģ¼

-0.14

ymous

-0.14

 sens

-0.14

hra

-0.14

lok

-0.14

igu

-0.14

Fib

-0.13

annah

-0.13

POSITIVE LOGITS

ÙĩÙĨ

0.20

yll

0.15

llib

0.14

dej

0.14

McM

0.14

.SYSTEM

0.14

.scalablytyped

0.14

otec

0.14

ilent

0.14

leur

0.13

Activations Density 0.029%

markers for data retrieval or citation references

No Comments

No Known Activations