INDEX

Explanations

question marks and their variations indicating uncertainty or inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ouser

-0.17

idas

-0.16

pite

-0.15

.readValue

-0.15

Globals

-0.15

mart

-0.15

orer

-0.15

ohen

-0.14

ivr

-0.14

 Demir

-0.14

POSITIVE LOGITS

ling

0.15

 Ð·Ð°ÑģÑĤ

0.15

bolt

0.14

eÄį

0.14

ORT

0.14

quam

0.14

 cazzo

0.14

ÑĨÐ¸

0.13

 Sexo

0.13

 Canary

0.13

Activations Density 0.009%

question marks and their variations indicating uncertainty or inquiries

No Comments

No Known Activations