INDEX

Explanations

evaluative phrases and descriptors

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

 Catal

-0.16

arg

-0.16

izin

-0.15

 Schwarz

-0.15

Arg

-0.15

arg

-0.15

NullException

-0.14

ected

-0.13

anta

-0.13

 Twin

-0.13

POSITIVE LOGITS

 description

0.17

uger

0.15

»

0.15

adesh

0.15

atch

0.14

.strict

0.14

description

0.14

´

0.14

 applied

0.14

-description

0.14

Activations Density 0.072%

evaluative phrases and descriptors

No Comments

No Known Activations