INDEX

Explanations

phrases that indicate uncertainty or conditions related to risks and outcomes

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

freeze

-0.15

.transfer

-0.15

ased

-0.14

uÄį

-0.14

uc

-0.14

ucle

-0.13

sse

-0.13

inke

-0.13

ertainment

-0.13

adel

-0.13

POSITIVE LOGITS

aben

0.14

Ð´Ð°Ñħ

0.14

.sponge

0.14

CONDS

0.13

 ÙĪØ§ÙĦØ³

0.13

 entreprise

0.13

 Michaels

0.13

alfa

0.13

 addCriterion

0.13

Inlining

0.13

Activations Density 0.005%

phrases that indicate uncertainty or conditions related to risks and outcomes

No Comments

No Known Activations