INDEX

Explanations

expressions that indicate necessity or requirements

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

Ð¾ÑĤÐ¾Ð²

-0.15

Å¯

-0.15

ixo

-0.14

Ð°ÑĤÑĥ

-0.14

esc

-0.14

arger

-0.13

ESC

-0.13

orb

-0.13

amen

-0.13

attice

-0.13

POSITIVE LOGITS

lessly

0.15

imal

0.14

zial

0.14

abal

0.14

Ã¶ff

0.14

itial

0.14

áº¥c

0.14

0.13

kes

0.13

/request

0.13

Activations Density 0.053%

expressions that indicate necessity or requirements

No Comments

No Known Activations