INDEX

Explanations

references to brands or labels in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

brid

-0.15

arks

-0.15

amedi

-0.14

 clad

-0.14

 manual

-0.14

elves

-0.14

ghi

-0.13

å¹¹ç·ļ

-0.13

ÙĦÙĪ

-0.13

 grounding

-0.13

POSITIVE LOGITS

Coc

0.15

cone

0.15

jde

0.15

ivate

0.14

eton

0.14

ervoir

0.14

tical

0.14

roup

0.14

Ø·Ø±

0.14

wayne

0.13

Activations Density 0.006%

references to brands or labels in the text

No Comments

No Known Activations