INDEX

Explanations

forms of the verb "to be" in different tenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

azzi

-0.15

yor

-0.14

owy

-0.14

uyáº¿t

-0.14

itness

-0.13

è¸ı

-0.13

PLL

-0.13

dbe

-0.13

ÏĢÎµ

-0.13

usp

-0.13

POSITIVE LOGITS

Å¡ti

0.18

raq

0.16

enes

0.15

ClientRect

0.15

chied

0.15

yscale

0.15

amil

0.14

 dang

0.14

otate

0.14

ãĤ¿ãĥ³

0.14

Activations Density 0.021%

forms of the verb "to be" in different tenses

No Comments

No Known Activations