INDEX

Explanations

variable assignments and object instantiations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

addin

-0.16

filer

-0.15

iliz

-0.15

nym

-0.15

ISA

-0.14

ÌĤ

-0.14

rif

-0.14

strom

-0.14

bid

-0.14

arrow

-0.14

POSITIVE LOGITS

Sil

0.17

eya

0.16

pd

0.15

ki

0.15

ered

0.14

asi

0.14

_MATH

0.14

sil

0.14

imson

0.14

PD

0.14

Activations Density 0.055%

variable assignments and object instantiations in code

No Comments

No Known Activations