INDEX

Explanations

phrases expressing abilities or the capacity to take action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ransition

-0.15

æĭľ

-0.14

Val

-0.14

hte

-0.13

.Library

-0.13

zcze

-0.13

olen

-0.13

clusion

-0.13

ordes

-0.13

hl

-0.13

POSITIVE LOGITS

 afford

0.20

 stomach

0.17

lassen

0.17

 HANDLE

0.15

 possibly

0.15

 hazard

0.15

_aff

0.15

 handle

0.14

’t

0.14

å®¹

0.14

Activations Density 0.148%

phrases expressing abilities or the capacity to take action

No Comments

No Known Activations