INDEX

Explanations

phrases related to evaluations and assessments of objects or actions

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

anter

-0.16

eful

-0.15

cing

-0.15

cion

-0.14

utomation

-0.14

abelle

-0.14

lage

-0.14

inar

-0.14

ety

-0.14

yn

-0.14

POSITIVE LOGITS

addon

0.18

ãģķãģ¾

0.16

ogui

0.14

ori

0.14

½Ķ

0.14

uve

0.14

prs

0.14

IPC

0.13

Ach

0.13

ìĥĿ

0.13

Activations Density 0.037%

phrases related to evaluations and assessments of objects or actions

No Comments

No Known Activations