INDEX

Explanations

references to media outlets and their editorial stances

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

èŃ

-0.18

okud

-0.16

 ModelState

-0.15

istrovstvÃŃ

-0.15

arkin

-0.14

/INFO

-0.14

Ã¡tor

-0.14

/wiki

-0.14

 medium

-0.14

erosis

-0.14

POSITIVE LOGITS

anca

0.15

lep

0.14

enties

0.13

_dispatch

0.13

GenerationStrategy

0.13

esis

0.13

ascript

0.13

aptops

0.13

Panel

0.13

afd

0.13

Activations Density 0.380%

references to media outlets and their editorial stances

No Comments

No Known Activations