INDEX

Explanations

references to files and directories related to testing in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

uche

-0.17

stor

-0.17

anford

-0.16

asl

-0.15

emann

-0.15

aton

-0.15

tons

-0.15

alus

-0.15

 Sist

-0.15

oust

-0.15

POSITIVE LOGITS

IENTATION

0.16

.cgi

0.14

illos

0.14

AEA

0.14

.scalablytyped

0.14

İ·

0.14

arkin

0.14

.openConnection

0.14

ioxide

0.14

_marks

0.14

Activations Density 0.107%

references to files and directories related to testing in a coding context

No Comments

No Known Activations