INDEX

Explanations

terms related to the application of principles or concepts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

/umd

-0.17

ColumnInfo

-0.16

ANCH

-0.15

Ã¼r

-0.15

aln

-0.15

iska

-0.14

nech

-0.14

anch

-0.14

aksi

-0.14

ovel

-0.14

POSITIVE LOGITS

å±ĭ

0.16

0.14

.measure

0.14

consistent

0.14

á»¥

0.13

è°±

0.13

 critique

0.13

ÎµÏĨ

0.13

Activations Density 0.068%

terms related to the application of principles or concepts in various contexts

No Comments

No Known Activations