INDEX

Explanations

phrases that indicate a beginning or initiation of events and activities

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

atra

-0.16

ODB

-0.15

rush

-0.15

aket

-0.15

áº¯t

-0.14

hb

-0.14

inha

-0.14

ssi

-0.14

.erb

-0.14

aka

-0.14

POSITIVE LOGITS

erset

0.15

uar

0.15

yr

0.15

 Rocky

0.14

venir

0.14

eg

0.14

imes

0.14

::*

0.14

 incl

0.14

Double

0.14

Activations Density 0.014%

phrases that indicate a beginning or initiation of events and activities

No Comments

No Known Activations