INDEX

Explanations

instances of the letter 'S' and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

akra

-0.17

mts

-0.15

BASH

-0.15

erosis

-0.15

avy

-0.15

aki

-0.15

otts

-0.14

 Hindered

-0.14

 áº¤

-0.14

edImage

-0.14

POSITIVE LOGITS

.Dot

0.16

AsyncResult

0.14

ylko

0.14

EG

0.13

 PROVIDED

0.13

AMESPACE

0.13

ammers

0.13

 inner

0.13

Activations Density 0.010%

instances of the letter 'S' and its variations in different contexts

No Comments

No Known Activations