INDEX

Explanations

references to technological terms and phrases related to data or identification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HEEL

-0.15

ieee

-0.15

hec

-0.15

HE

-0.14

Hd

-0.14

.IsAny

-0.14

ÅĽÄĩ

-0.14

hel

-0.14

_ENC

-0.13

POSITIVE LOGITS

Smy

0.15

uitka

0.15

onal

0.15

NS

0.15

ãĤ·ãĥ§

0.15

à¥ĭà¤§

0.14

onde

0.13

asio

0.13

#echo

0.13

Activations Density 0.022%

references to technological terms and phrases related to data or identification processes

No Comments

No Known Activations