INDEX

Explanations

phrases indicating a substantial quantity or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

oppable

-0.15

dens

-0.14

icken

-0.13

emens

-0.13

aldo

-0.13

Äįel

-0.13

icot

-0.13

halb

-0.13

 ever

-0.13

icc

-0.13

POSITIVE LOGITS

ãĤĿ

0.15

ulin

0.15

 sayÄ±da

0.14

Ø±ÙĪØ¯

0.14

 happening

0.14

FH

0.14

ypes

0.14

angent

0.13

arget

0.13

abin

0.13

Activations Density 0.072%

phrases indicating a substantial quantity or emphasis

No Comments

No Known Activations