INDEX

Explanations

numbers indicating game scores, wins, and losses in sports contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uard

-0.17

gom

-0.16

ie

-0.16

oj

-0.15

nen

-0.15

forge

-0.15

osy

-0.14

-ÑĤÐ¾

-0.14

mond

-0.14

POSITIVE LOGITS

iyon

0.17

oland

0.15

/-

0.15

obe

0.15

asbourg

0.14

ï¼ĪæĺŃåĴĮ

0.14

 McMahon

0.14

achat

0.14

LOB

0.13

.au

0.13

Activations Density 0.025%

numbers indicating game scores, wins, and losses in sports contexts

No Comments

No Known Activations