INDEX

Explanations

phrases that suggest uncertainty or ambiguity in research outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

spec

-0.16

.func

-0.14

ç£

-0.13

arton

-0.13

 Capitals

-0.13

 Blank

-0.13

-0.12

 Guth

-0.12

)ãĢģ

-0.12

POSITIVE LOGITS

CoreApplication

0.16

uur

0.16

clerosis

0.15

abwe

0.14

rych

0.14

LOPT

0.14

mdir

0.14

eprom

0.14

 hopefully

0.13

.opensource

0.13

Activations Density 0.300%

phrases that suggest uncertainty or ambiguity in research outcomes

No Comments

No Known Activations