INDEX

Explanations

references to the band Pink Floyd and related musical terminology

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

 Budd

-0.17

bidden

-0.15

ativ

-0.15

 æ¤

-0.14

reau

-0.14

 Finder

-0.13

king

-0.13

åĨĬ

-0.13

\API

-0.13

commended

-0.13

POSITIVE LOGITS

 Harmony

0.15

birth

0.15

 Klopp

0.14

 quad

0.14

CL

0.14

 itself

0.14

oop

0.14

pla

0.14

enia

0.13

vil

0.13

Activations Density 0.231%

references to the band Pink Floyd and related musical terminology

No Comments

No Known Activations