INDEX

Explanations

strong adjectives and phrases indicating intensity or degree

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Found

-0.17

ickey

-0.15

ella

-0.15

och

-0.15

Found

-0.14

 navr

-0.14

ueur

-0.14

<UnityEngine

-0.13

lander

-0.13

ILT

-0.13

POSITIVE LOGITS

eder

0.16

Insn

0.15

LEM

0.15

 ones

0.15

igan

0.15

 Ones

0.14

 Chapel

0.13

_VOID

0.13

ramework

0.13

 thereof

0.13

Activations Density 0.161%

strong adjectives and phrases indicating intensity or degree

No Comments

No Known Activations