INDEX

Explanations

copyright symbols and related references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icks

-0.15

Mej

-0.15

isci

-0.15

 Simulation

-0.15

 spatial

-0.14

kr

-0.14

olan

-0.14

yan

-0.14

atz

-0.14

POSITIVE LOGITS

ãĥĮ

0.16

cak

0.16

MethodImpl

0.16

eries

0.15

UDGE

0.15

appings

0.15

_VO

0.15

ãĤ

0.15

ReturnValue

0.14

ãĢģç§ģ

0.14

Activations Density 0.003%

copyright symbols and related references

No Comments

No Known Activations