INDEX

Explanations

phrases related to progression or advancement into new contexts or frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ø§ÙĨÛĮØ§

-0.14

 subt

-0.14

chten

-0.14

.XR

-0.14

.INSTANCE

-0.14

redi

-0.14

elor

-0.13

ruc

-0.13

iÃ©n

-0.13

erty

-0.13

POSITIVE LOGITS

SSION

0.14

ç¥¥

0.14

 priv

0.14

Gin

0.13

íļ

0.13

Mixin

0.13

uppe

0.13

OCR

0.13

/manual

0.13

ãĥ¼ãĥį

0.13

Activations Density 0.027%

phrases related to progression or advancement into new contexts or frameworks

No Comments

No Known Activations