INDEX

Explanations

mathematical expressions involving logarithmic functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

fir

-0.15

earable

-0.15

ega

-0.15

fur

-0.15

efa

-0.14

 Operation

-0.14

ows

-0.14

wor

-0.14

imar

-0.14

POSITIVE LOGITS

bis

0.16

istrovstvÃŃ

0.15

_routing

0.15

.TryParse

0.15

arend

0.14

umlu

0.14

ÚĨÛĮ

0.14

ÑĥÐ¼Ð¾Ð²

0.14

rava

0.14

DonaldTrump

0.14

Activations Density 0.017%

mathematical expressions involving logarithmic functions

No Comments

No Known Activations