INDEX

Explanations

terminology and concepts related to language, translation, and interpretation

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

ADR

-0.16

enda

-0.15

ime

-0.14

/routes

-0.14

areth

-0.14

baugh

-0.14

VERR

-0.13

Gan

-0.13

 alive

-0.13

POSITIVE LOGITS

nard

0.18

estar

0.16

ards

0.15

ÃŃsk

0.14

Ã»

0.14

ãĥ«ãĥķ

0.14

 Osama

0.14

íİ¸

0.14

otine

0.14

 Franken

0.14

Activations Density 0.076%

terminology and concepts related to language, translation, and interpretation

No Comments

No Known Activations