INDEX

Explanations

words related to linguistics and the study of language

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ertas

-0.16

ÑħÑĥ

-0.15

/gtest

-0.14

pler

-0.14

ipc

-0.14

 gÃ³

-0.14

AYER

-0.14

 åī

-0.14

ctors

-0.14

ayer

-0.14

POSITIVE LOGITS

nom

0.15

 bomb

0.14

gro

0.14

gas

0.14

oct

0.14

amam

0.14

 nominal

0.14

Ð°ÑĢÑħ

0.14

lor

0.13

anon

0.13

Activations Density 0.002%

words related to linguistics and the study of language

No Comments

No Known Activations