INDEX

Explanations

superlative expressions indicating size, influence, or quality

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

asal

-0.14

edn

-0.14

fen

-0.14

olon

-0.14

{:

-0.14

 sund

-0.13

ëĶ©

-0.13

ç¥¥

-0.13

 incon

-0.13

 anale

-0.13

POSITIVE LOGITS

uster

0.15

oine

0.15

ÎĦ

0.15

bil

0.15

Bil

0.15

æĶ¹

0.15

opoulos

0.15

 finely

0.14

ignum

0.14

loi

0.14

Activations Density 0.027%

superlative expressions indicating size, influence, or quality

No Comments

No Known Activations