INDEX

Explanations

terms related to scanning and measurement processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lein

-0.16

<::

-0.15

ÑģÑı

-0.14

à¦°

-0.14

çļ

-0.14

irs

-0.14

%%%

-0.14

enc

-0.14

anch

-0.14

Ã¼yÃ¼k

-0.13

POSITIVE LOGITS

atics

0.16

izr

0.15

illas

0.15

ewire

0.15

Ìĥ

0.14

PPER

0.14

pell

0.14

Eh

0.14

hic

0.14

Ð¾ÑģÑĤÐ¸

0.13

Activations Density 0.011%

terms related to scanning and measurement processes

No Comments

No Known Activations

terms related to scanning and measurement processes

No Comments

No Known Activations