INDEX

Explanations

nouns and terms related to learning and educational frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

itat

-0.16

burger

-0.14

inning

-0.14

itates

-0.14

inx

-0.14

bjerg

-0.13

stag

-0.13

 fantas

-0.13

inf

-0.13

ãģķãĤī

-0.13

POSITIVE LOGITS

evin

0.14

Utf

0.14

 Rent

0.13

ãĥ¼ãĥĭ

0.13

 ØªØµ

0.13

áº¿

0.13

.Logic

0.13

.Named

0.13

FML

0.13

½æķ°

0.13

Activations Density 0.044%

nouns and terms related to learning and educational frameworks

No Comments

No Known Activations