INDEX

Explanations

dialogue and interactions involving questions and discussions about memories or past experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

edl

-0.16

atif

-0.15

olib

-0.15

 Blasio

-0.15

ActionCreators

-0.14

rana

-0.14

lse

-0.13

 NUITKA

-0.13

emey

-0.13

ettle

-0.13

POSITIVE LOGITS

0.14

ì¦

0.12

Å¾i

0.12

Ro

0.12

 AndAlso

0.12

CAC

0.12

.openConnection

0.12

 Underground

0.12

?p

0.12

.notify

0.12

Activations Density 1.602%

dialogue and interactions involving questions and discussions about memories or past experiences

No Comments

No Known Activations