INDEX

Explanations

references to coding actions and executions

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

yne

-0.15

hin

-0.15

yled

-0.15

asy

-0.14

quier

-0.14

enne

-0.14

wis

-0.14

enders

-0.14

archy

-0.14

cratch

-0.14

POSITIVE LOGITS

_PIPELINE

0.16

utar

0.15

haft

0.15

 Mezi

0.15

otoxic

0.15

 Baghd

0.14

iteur

0.14

_queues

0.14

ecimal

0.14

.zoom

0.14

Activations Density 0.054%

references to coding actions and executions

No Comments

No Known Activations