INDEX

Explanations

nouns and proper names related to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

elyn

-0.16

.FontStyle

-0.15

Ãły

-0.15

Ð´Ñı

-0.15

 kÃ¥

-0.15

OLS

-0.15

atk

-0.14

å¬

-0.14

athy

-0.14

Unified

-0.14

POSITIVE LOGITS

ãĥ³ãĤ¬

0.16

elp

0.15

nde

0.15

 Lions

0.14

ayment

0.14

åĩĨ

0.14

nab

0.14

 Adrian

0.13

fol

0.13

anga

0.13

Activations Density 0.041%

nouns and proper names related to various contexts

No Comments

No Known Activations