INDEX

Explanations

occurrences of the word "select" and various forms of the word "viving" (such as "living")

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

 Tort

-0.18

rai

-0.16

lun

-0.15

:"-"`↵

-0.14

epend

-0.14

alloc

-0.14

 Torres

-0.14

acas

-0.14

 Kurul

-0.14

armor

-0.14

POSITIVE LOGITS

hw

0.16

etros

0.15

 Bret

0.14

roit

0.14

 retro

0.14

roat

0.14

áº½

0.13

etrofit

0.13

oland

0.13

etro

0.13

Activations Density 0.007%

occurrences of the word "select" and various forms of the word "viving" (such as "living")

No Comments

No Known Activations